speech to text live stream

Real-Time Transcription

Create a better user experience with the most accurate live transcription and subtitling

Instantly transcribe speech to text for live audio and video

Agora’s Real-Time Transcription provides accurate live transcription and subtitling services at a low cost.

Reduce cost and increase efficiency

Channel-based live transcription allows you to distribute live captions to all participants in channel while only paying for the duration of a channel—not the number of users. This approach is far more efficient and lower cost when compared to traditional client-side live transcription.

Get the most accurate results at scale

Cutting-edge AI ensures the highest accuracy even with overlapping speech, regional accents, and poor network conditions. Scale from one-to-one meetings to up to millions of participants with the same accuracy.

Integrate with ease

Simple API integration for a full solution supporting transcription from audio to text, live captioning, and cloud recording with closed captioning (CC) that works on any device. Extend with new features using the Restful API.

Features 

Live transcription for rtc.

Integrated with Agora’s voice and video service, live transcription and captions improve accessibility for your audience. Perfect for meetings, live streaming, lectures, interviews, live shopping, and more.

Channel-based cloud transcription

Cloud transcription service converts audio to text based on channel and distributes the text to all participants in this channel to show live closed captions (CC). Transcripts are saved to the cloud.

Transcribing and labeling simultaneous speakers

Easily label who said what—even with up to 3 simultaneous speakers. Separate transcription for each host ensures accurate voice transcription with multiple hosts.

Captioning for cloud recordings

Transcribe audio to text on video recordings to enable closed captions (CC) and review important discussion items in the transcript.

Multi-language support

Real-time transcription supports all major languages and dialects, and each channel can support audio to text transcription for up to two languages simultaneously.

Enterprise-grade security and compliance

Agora is ISO and SOC 2 certified and meets compliance standards for regional privacy laws and industry regulations, including GDPR, CCPA, and HIPAA.

Made for developers

Agora’s Real-Time Transcription platform-agnostic RESTful APIs make it easy to add highly accurate, cost-effective audio transcription capabilities to your app on any platform.

Transcribe speech to text for any live meetings or events

Securely transcribe and record real-time audio or video and organize recordings and transcripts to speed up workflows.

Education  

Give faculty and students real-time captions and notes for in-person and virtual lectures, classes or meetings.

Virtual Meetings

Provide real-time automated notes in meetings and conversations to keep everyone aligned in a remote work environment.

Social & Metaverse  

Eliminate communication barriers for people with different languages or disabilities.

Increase accessibility to reach a wider audience and improve discoverability for brands and hosts.  

Keep secure records of virtual appointments and patient questions with the most accurate speech to text software.

Events  

Empower your event with real-time, accurate notes, ensuring a more accessible, searchable, and engaging event experience.

Add live transcription to your real-time experience today

Get 1,000 minutes FREE 

Speech-to-Text live streaming for live captions, powered by the world's leading speech recognition API

Rev AI's live streaming Speech-to-Text engine powers real-time captioning for your business. Our captions ensure that live talks and trainings are accessible and can be archived for future use.

Get your transcription in real-time with Rev AI's streaming API.

Rev AI serves your industry

Our single English model supports all major English accents from around the world, eliminating the need to pay extra and switch models for different speakers and conversations. We provide you with the best English results out-of-the-box, regardless of who is speaking. More languages coming soon.

Transcend barriers of communication with Rev AI

True Real-Time Transcription

Massive amounts of speech data are being generated online every day. speechly for transcription enables you to process this data accurately, cost-efficiently and in real-time., why you’ll love it, industry leading accuracy.

Easily train Speech-to-Text models for your specific domain with industry leading 95%+ accuracy.

Cost-efficient

Our proprietary technology allows you to run transcription on-device instead of in the cloud, resulting in 1/100 of the cost vs cloud-based solutions.

Real-time Transcription

Using our streaming technology, we can deliver high quality transcripts within a few hundred milliseconds.

Batch Transcription

If you have pre-recorded audio or video content that needs a transcript, Speechly can also process massive amounts of data asynchronously.

Podcasts and Audio Streams

Using Speechly, you can easily transcribe speech on the users’ device, resulting in a cost-efficient solution for transcribing large amounts of audio content. All in real-time and with industry leading accuracy.

Videos and Streaming

Using Speechly you know exactly what is being said in videos and streams in real-time. By running Speechly on-device, you can cost-efficiently scale across any and all video platforms.

Built by researchers intent on enabling better voice experiences

Our patented technology works in real-time, powering everything from on-site voice search to voice command and control.

We’re here to help your business get the most value out of voice

Flexible pricing with no hidden fees.

Get started with Speechly

Learn how to create a Speechly application and transcribe both live and pre-recorded audio with our getting started guide.

A new standard for AI powered live captions

Add flawless closed captions to your live stream through automatic speech-to-text conversion.

Our AI powered captioning solution is easy to use, reliable and efficient. Its unique speech-to-text technology, with optional support for human real-time correction, makes your captions more accurate and readable than ever.

Unique speech-to-text technology

Our technology for auto-generating closed captions leverages the latency that comes with the HTTP Live Streaming protocol. By slightly increasing it, we achieve a triple goal:

• Longer audio streams can be sent to the Automatic Speech Recognition (ASR) engine. This allows the ASR engine to better interpret the words and construct correct phrases and sentences. This increases the accuracy of the conversion.
• Optionally, a human editor can make real-time corrections to the automatically generated captions, before they are translated and shown in the live stream.
• Clevercast has slightly more time to process the ASR output. This allows us to improve the readability of the captions and makes them easier to understand .

Most accurate live captions available

For an indication of the difference in accuracy and readability with other platforms, we recorded the same live stream with auto-generated captions in Clevercast, YouTube and Vimeo. All recordings are unedited.

The live stream featured a number of different speakers, each with their own speech pattern and accent.

Note that Clevercast features to improve caption accuracy, such as keyword vocabularies and real-time correction, were NOT used during this test. All captions were generated fully automatically in real-time, without human intervention.

If you want to assess the quality of our live closed captions firsthand, don’t hesitate to request a trial account .

Above are unedited recordings of the same live stream with auto-generated captions in Clevercast, YouTube and Vimeo. The demo uses excerpts from the following videos available June 20, 2023 under a CC-BY 4.0 license:

Paywall: The Business of Scholarship by Jason Schmitt Will saving poor children lead to overpopulation? Free material from WWW.GAPMINDER.ORG

Real-time correction for 100% accuracy

Even though the accuracy of speech-to-text conversion is already very high, some live streams require perfection. That’s why Clevercast offers a real-time correction interface .

The cloud interface lets you edit the AI generated captions in real-time , just before they are sent to the live stream (and translated into other languages). It lets you change words and move them to different lines for improved readibility.

Making these corrections is a simple task that requires no experience or training . Our intuitive interface allows anyone to edit the captions in a browser with mouse and keyboard.

Intelligent caption rendering in the player

Because of the increased latency, Clevercast can add the captions to the live stream in an intelligent manner. This allows Clevercast player to show (partial) sentences, rather than separate words . This makes the closed captions easier to read and understand.

Viewers, anywhere in the world, can watch the live stream and select their preferred caption language in our video player. Our customizable HTML5 player can be easily embedded into any device and platform. Just copy the embed code from Clevercast.

Alternatively, you can choose to display the rolling text in a separate widget . This widget also allows your viewers to change their preferred language.

Live AI translation to other languages

Clevercast can automatically translate closed captions in real-time and make the additional languages available in the live stream.

The accuracy of the translations mostly depends on the quality of the source captions. With an accurate source, all extra languages – even unpopular ones – will be translated with an 99.9+% accuracy . Note that when using our correction interface, the corrected captions will be used as the source for translation.

Alternatively, you can also use a professional captioner for the source language, combined with AI translation for the extra languages.

Cloud recording and Video on-Demand

Clevercast makes a cloud recording of the multilingual live stream, which can be downloaded. All caption languages can be downloaded as WebVTT files . This allows you to upload them to YouTube or social media channels for on-demand viewing.

You can also convert the cloud recording of your live stream to Video on-Demand (VoD). Our VoD player with all closed captions can be added to your site or platform by copying the embed code for your event.

Let us assist you

If you have no experience with automatically generated closed captions and are not sure whether it is the right choice for your event, don’t hesitate to contact us .

We can help you review your options and provide the necessary tips. If desired, we can offer professional correctors for your event, communicate with them, provide them with all the relevant documentation and monitor your live stream.

Get Started Now

Start live streaming today with a solution of choice. No credit card required.

Or contact us for more info.

Transcribing streaming audio

Using Amazon Transcribe streaming, you can produce real-time transcriptions for your media content. Unlike batch transcriptions, which involve uploading media files, streaming media is delivered to Amazon Transcribe in real time. Amazon Transcribe then returns a transcript, also in real time.

Streaming can include pre-recorded media (movies, music, and podcasts) and real-time media (live news broadcasts). Common streaming use cases for Amazon Transcribe include live closed captioning for sporting events and real-time monitoring of call center audio.

Streaming content is delivered as a series of sequential data packets, or 'chunks,' that Amazon Transcribe transcribes instantaneously. The advantages of using streaming over batch include real-time speech-to-text capabilities in your applications and faster transcription times. However, this increased speed may have accuracy limitations in some cases.

Amazon Transcribe offers the following options for streaming:

SDKs (preferred)

AWS Management Console

To transcribe streaming audio in the AWS Management Console, speak into your computer microphone.

For SDK code examples, refer to the AWS Samples repository on GitHub.

Audio formats supported for streaming transcriptions are:

OPUS-encoded audio in an Ogg container

PCM (only signed 16-bit little-endian audio formats, which does not include WAV)

Lossless formats (FLAC or PCM) are recommended.

Streaming transcriptions are not supported with all languages. Refer to the 'Data input' column in the supported languages table for details.

To view the Amazon Transcribe Region availability for streaming transcriptions, see: Amazon Transcribe Endpoints and Quotas .

Best practices

The following recommendations improve streaming transcription efficiency:

If possible, use PCM-encoded audio.

Ensure that your stream is as close to real-time as possible.

Latency depends on the size of your audio chunks. If you're able to specify chunk size with your audio type (such as with PCM), set each chunk to between 50 ms and 200 ms. You can calculate the audio chunk size by the following formula:

Use a uniform chunk size.

Make sure you correctly specify the number of audio channels.

With single-channel PCM audio, each sample consists of two bytes, so each chunk should consist of an even number of bytes.

With dual-channel PCM audio, each sample consists of four bytes, so each chunk should be a multiple of 4 bytes.

When your audio stream contains no speech, encode and send the same amount of silence. For example, silence for PCM is a stream of zero bytes.

Make sure you specify the correct sampling rate for your audio. If possible, record at a sampling rate of 16,000 Hz; this provides the best compromise between quality and data volume sent over the network. Note that most high-end microphones record at 44,100 Hz or 48,000 Hz.

To use the Amazon Web Services Documentation, Javascript must be enabled. Please refer to your browser's Help pages for instructions.

Thanks for letting us know we're doing a good job!

If you've got a moment, please tell us what we did right so we can do more of it.

Thanks for letting us know this page needs work. We're sorry we let you down.

If you've got a moment, please tell us how we can make the documentation better.

Latest reviews

• Search resources
• OBS Studio Plugins

LocalVocal: Local Live Captions & Translation On-the-Go v0.2.1

• Author royshilkrot
• Creation date Aug 14, 2023

• Transcribe audio to text in real time in 100 languages
• Translate immediately to/from ~100 languages
• Display captions on screen using text sources
• Translate captions in real time to any language - see https://youtu.be/Q34LQsx-nlg or https://youtu.be/ryWBIEmVka4
• Remove unwanted words from the transcription
• Summarize the text and show "highlights" on screen
• Detect key moments in the stream and allow triggering events (like replay)
• Detect emotions/sentiment and allow triggering events (like changing the scene or colors etc.)
• Background Removal removes background from webcam without a green screen.
• Detect will detect and track >80 types of objects in real-time inside OBS
• URL/API Source that allows fetching live data from an API and displaying it in OBS.

More resources from royshilkrot

Share this resource

Latest updates, v0.2.1 - translation built-in, v0.2.0 - cuda on windows mac apple arm optimization, v0.1.1 - new whisper, variable buffer, bugfix 7.1 audio.

• 5.00 star(s)
• Feb 25, 2024
• Version: v0.1.0
• Dec 18, 2023
• Version: v0.0.7

• Sep 18, 2023
• Version: v0.0.2
• This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register. By continuing to use this site, you are consenting to our use of cookies. Accept Learn more…

Live Transcribing Phone Calls using Twilio Media Streams and Google Speech-to-Text

Time to read: 5 minutes

• Facebook logo
• Twitter Logo Follow us on Twitter
• LinkedIn logo

With Twilio Media Streams, you can now extend the capabilities of your Twilio-powered voice application with real time access to the raw audio stream of phone calls. For example, we can build tools that transcribe the speech from a phone call live into a browser window, run sentiment analysis of the speech on a phone call or even use voice biometrics to identify individuals.

This blog post will guide you step-by-step through transcribing speech from a phone call into text, live in the browser using Twilio and Google Speech-to-Text  with Node.js.

If you want to skip the step-by-step instructions, you can clone my Github Repository  and follow the ReadMe to get setup or if you prefer to watch Video, check out a video walkthrough here.

Requirements

Before we can get started, you’ll need to make sure to have:

• A Free Twilio  Account
• A Google Cloud Account
• Installed ngrok
• Installed the Twilio CLI

Setting up the Local Server

Twilio Media Streams use the WebSocket API  to live stream the audio from the phone call to your application. Let’s get started by setting up a server that can handle WebSocket connections.

Open your terminal and create a new project folder and create an index.js file.

To handle HTTP requests we will use node’s built-in http module and Express . For WebSocket connections we will be using ws , a lightweight WebSocket client for node.

In the terminal run these commands to install ws and Express :

Open your index.js file and add the following code to set up your server.

Save and run index.js with node index.js . Open your browser and navigate to http://localhost:8080 . Your browser should show Hello World .

Now that we know HTTP requests are working, let’s test our WebSocket connection. Open your browser’s console and run this command:

If you go back to the terminal you should see a log saying New Connection Initiated .

Setting up Phone Calls

Let’s set up our Twilio number to connect to our WebSocket server.

First we need to modify our server to handle the WebSocket messages  that will be sent from Twilio when our phone call starts streaming. There are four main message events we want to listen for: connected`, `start`, `media` and `stop`.

• Connected: When Twilio makes a successful WebSocket connection to a server
• Start: When Twilio starts streaming Media Packets
• Media: Encoded Media Packets (This is the Raw Audio)
• Stop: When streaming ends the stop event is sent.

Modify your index.js file to log messages when each of these messages arrive at our server.

Now we need to set up or Twilio number to start streaming audio to our server. We can control what happens when we call our Twilio number using TwiML . We’ll create a HTTP route that will return TwiML` instructing Twilio to stream audio from the call to our server.

Add the following POST route to your index.js file.

For Twilio to connect to your local server we need to expose the port to the internet. The easiest way to do that is using the Twilio CLI. Open a new Terminal to continue.

First let’s buy a phone number. In your terminal run the following command. I have used the GB country code to buy a mobile number, but feel free to change this for a number local to you.  Hold on to the number’s Friendly Name   once the response is returned.

Finally lets update the phone number to point to our localhost url. We need to use ngrok to create a tunnel to our localhost port and expose it to the internet. In a new terminal window run the following command:

You should get an output with a forwarding address like this. Copy the URL onto the clipboard. Make sure you record the https url.

Back in the terminal window where we bought our twilio number lets update our phone number to make a post http request to our server.

Run the following command:

Head over to a new terminal window and run your index.js file. Now call your Twilio phone number and you should hear the following prompt, “I will stream the next 60 seconds of audio through your websocket”. The terminal should be logging  Receiving Audio…

NOTE: Make sure that you have at least 2 terminals running if your log doesn’t match the expected response. One running your server (index.js) and one running ngrok.

Transcribing Speech into Text

At this point we have audio from our call streaming to our server. Today, we’ll be using Google Cloud Platform’s Speech-to-Text API  to transcribe the voice data from the phone call.

There is some setup that we need to do before we get started.

• Install and initialize the Cloud SDK
• Setup a new GCP Project
• Create or select a project.
• Enable the Google Speech-to-Text API for that project.
• Create a service account.
• Download a private key as JSON.
• Set t he environment variable   GOOGLE_APPLICATION_CREDENTIALS to the file path of the JSON file that contains your service account key. This variable only applies to your current shell session, so if you open a new session, set the variable again.

Run the following command to install the Google Cloud Speech-to-Text client libraries.

Now let’s use it in our code.

First we’ll include the Speech Client from the Google Speech-to-Text library then we will configure a Transcription Request . In order to get live transcription results, make sure you set interimResults to true. I have also set the language code to en-GB , feel free to set yours to a different language region .

Now let’s create a new stream to send audio from our server to the Google API. We will call it the recognizeStream and we will write our audio packets from our phone call to this stream. When the call has ended we will call .destroy() to end the stream.

Edit your code to include these changes.

Restart your server, call your Twilio phone number and start talking down the phone. You should see interim transcription results begin to appear in your terminal.

Sending Live Transcription to the Browser

One of the benefits of using WebSockets is that we can broadcast messages to other clients, including browsers.

Let’s modify our code to broadcast our interim transcription results to all connected clients. We’ll also modify the GET route. Rather than sending ‘Hello World’ let’s send a   HTML file. We will need the path package also, so don’t forget to require it.

Modify your index.js file like below.

Let’s setup a web page to handle the interim transcriptions and display them in the browser.

Create a new file, index.html and include the following:

Restart your server, load localhost:8080 in your browser then give your Twilio phone number a call and watch your words begin to appear in your browser.

Wrapping up

Congratulations! You can now harness the power of Twilio media streams to extend your voice applications. Now that you have live transcription, try translating the text with Google’s Translate API  to create live speech translation or run sentiment analysis  on the audio stream to work out the emotions behind the speech.

If you have any questions, feedback or just want to show me what you build, feel free to reach out to me:

• Twitter: @chatterboxcoder
• GitHub: nokenwa
• Email: nokenwa@twilio.com

Related Posts

Related Resources

Twilio docs, from apis to sdks to sample apps.

API reference documentation, SDKs, helper libraries, quickstarts, and tutorials for your language and platform.

Resource Center

The latest ebooks, industry reports, and webinars.

Learn from customer engagement experts to improve your own communication.

Twilio's developer community hub

Best practices, code samples, and inspiration to build communications and digital engagement experiences.

Using real-time streaming

AssemblyAI's Streaming Speech-to-Text (STT) service allows you to transcribe live audio streams with high accuracy and low latency. By streaming your audio data to our secure WebSocket API, you can receive transcripts back within a few hundred milliseconds, and our system continues to revise these transcripts with greater accuracy over time as more context arrives.

In this guide, you'll learn how to establish a WebSocket connection, send audio data, and receive partial and final transcription results. For more information about the expected audio format, see Audio Requirements .

Get started ​

Before we begin, make sure you have an AssemblyAI account and an API key. You can sign up for a free account and get your API key from your dashboard. Please note that this feature is available for paid accounts only. If you're on the free plan, you'll need to upgrade.

The entire source code of this guide can be viewed here .

Step-by-step instructions ​

To use the microphone stream you need to install pyaudio . Mac and Linux users also need to install portaudio first. Additionally, install the websocket-client package:

In your code, first setup the microphone stream and then establish a WebSocket connection with the streaming endpoint by using a WebSocket client and connecting to wss://api.assemblyai.com/v2/realtime/ws .

Authenticate your request by including your API key in the authorization header of your WebSocket connection, and provide the sample rate of your audio data as a query parameter to the streaming endpoint.

Update the WebSocket's message event to load the incoming data as JSON and extract the text

Update the WebSocket's message event to print the transcript, conditionally prepended with a string that signifies if the transcript is partial or final.

Update the WebSocket's open event to stream data from the microphone.

Optional: Add up to 2,500 characters of custom vocabulary to your streaming session by including the word_boost parameter as an optional query parameter in the URL.

See also Adding Custom Vocabulary

Update the WebSocket's error event to handle WebSocket errors and application-level errors, including bad sample rate, authentication failure, insufficient funds, and more. See also Closing and Status Codes for a list of errors.

Additionally, update the WebSocket's close event.

Audio Requirements ​

The raw audio data must comply with a strict encoding format. This is because we don't do any transcoding to your data, we send it directly to the model for transcription to reduce latency. The encoding of your audio must be in:

• 16-bit signed integer PCM or mu-law encoding
• A sample rate that matches the value of the sample_rate query param you supply
• Single-channel
• 100 to 2000 milliseconds of audio per message

Audio segments with a duration between 100 ms and 450 ms produce the best results in transcription accuracy.

Specifying the encoding ​

By default, transcriptions expect PCM16 encoding. If you want to use mu-law encoding, you must set the encoding parameter to pcm_mulaw :

Request Types ​

These are the types of requests that can be sent to the WebSocket API.

Opening a Session ​

When opening a Session you can pass the following query attributes to the WebSocket URL:

sample_rate ​

The sample rate of the streamed audio.

Example: wss://api.assemblyai.com/v2/realtime/ws?sample_rate=16000

word_boost ​

See also Specifying the encoding

See also Creating Temporary Authentication Tokens

Sending Audio ​

When sending audio over the WebSocket connection, you can use the websocket's binary mode to send raw audio data. This can be the raw data recorded directly from a microphone or read from an audio file.

Sending audio_data via JSON is also supported but will be deprecated in the future. Use the binary mode instead.

Terminating a Session ​

When you've completed your session, clients should send a JSON message with the following field.

After requesting session termination, the server will send the remaining transcript messages, followed by a SessionTerminated message .

Response Types ​

These are the types of responses that can be received from the WebSocket API.

Session Start ​

Once your request is authorized and connection established, your client receives a SessionBegins message with the following JSON data:

Transcripts ​

Our Streaming Speech-to-Text pipeline uses a two-phase transcription strategy, broken into partial and final results.

Partial Transcripts ​

As you send audio data to the API, the API immediately starts responding with Partial Results. The following keys are returned from the WebSocket API.

Final Transcripts ​

After you've received your partial results, our model continues to analyze incoming audio and, when it detects the end of an "utterance" (usually a pause in speech), it'll finalize the results sent to you so far with higher accuracy, as well as add punctuation and casing to the transcription text.

The following keys are returned from the WebSocket API when Final Results are sent:

Session Terminated ​

After requesting session termination , the server will send the remaining transcript messages, followed by a SessionTerminated message. Your client receives a SessionTerminated message with the following JSON data:

Closing and Status Codes ​

The WebSocket specification provides standard errors .

Our API provides application-level WebSocket errors for well-known scenarios:

Quotas and Limits ​

The following limits are imposed to ensure performance and service quality.

• Idle Sessions - Sessions that don't receive audio within 1 minute will be terminated.
• Session Limit - 100 sessions at a time for paid users. Please contact us if you need to increase this limit. Free-tier users must upgrade their account to use real-time streaming.
• Session Uniqueness - Only one WebSocket per session.
• Audio Sampling Rate Limit - Customers must send data in near real-time. If a client sends data faster than 1 second of audio per second for longer than 1 minute, we'll terminate the session.

Adding Custom Vocabulary ​

Developers can also add up to 2500 characters of custom vocabulary to their real-time session by adding the optional query parameter word_boost in the URL. The parameter should map to a JSON encoded list of strings as shown in this Python example:

Creating Temporary Authentication Tokens ​

If you need to authenticate on the client, you can avoid exposing your API key by using temporary authentication tokens. Temporary tokens have a one-time use restriction. To generate a temporary token, send a POST request to https://api.assemblyai.com/v2/realtime/token . Use the expires_in parameter to specify how long the token should be valid for, in seconds.

The expires_in parameter must have a value between 60 and 360000 seconds.

In response you'll receive the following JSON output:

A developer can now use this temporary token in the browser to authenticate a new WebSocket session with the following endpoint wss://api.assemblyai.com/v2/realtime/ws?sample_rate=16000&token={New Temp Token} . For example:

Conclusion ​

Streaming Speech-to-Text is a powerful feature with even more powerful possibilities for integration. On the AssemblyAI blog, you can learn about using Streaming Speech-to-Text to:

• Automatically Transcribe Zoom Calls in Real Time
• Transcribe Twilio Phone Calls
• Connect to the Streaming Speech-to-Text API using a PyAudio stream

You can also find an example of using Express.js for Streaming Speech-to-Text on GitHub .

• Get started
• Step-by-step instructions
• Specifying the encoding
• Opening a Session
• Sending Audio
• Terminating a Session
• Session Start
• Transcripts
• Session Terminated
• Closing and Status Codes
• Quotas and Limits
• Adding Custom Vocabulary
• Creating Temporary Authentication Tokens

New & Improved Real-Time Transcription and Captioning With Rev.ai Streaming API

Rev › Blog › Transcription Blog › New & Improved Real-Time Transcription and Captioning With Rev.ai Streaming API

Earlier in 2019, we announced automatic speech-to-text services through the Rev platform. Today, we’re announcing real-time automated transcription and captioning services through our speech recognition software, Rev.ai.

While Rev.ai has previously enabled developers to easily integrate our speech recognition engine into their platforms and services, this new capability to process live audio and video for transcription and captioning is an industry game-changer.

So, what does real-time automated transcription and captions mean for your business? The implications reach far beyond the normal use case of our human-powered transcription and captioning services.

“We developed real-time audio transcription to meet market demand beyond the asynchronous market, and provide customers — from podcasters to call centers — with deeper speech to text capabilities.”

– Rev.ai General Manager, Jay Lee

With the Streaming API, you can add captions to live videos or display captions in real-time at conferences and events. It can also provide accurate transcriptions for keyword monitoring or implement an immediate action based on trigger words. However you might use it, real-time speech recognition offers huge benefits to new and existing Rev customers.

Benefits of Real-Time Captioning and Transcription

While human-powered transcription and captioning are the perfect solution for post-production, real-time captioning and transcription offer new and exclusive capabilities for your live productions and events.

Uses of Real-Time Voice-to-Text Services

Your business can use live captioning and transcription for many situations in real-time.

• Live videos, webinars, and podcasts captioned in real-time
• Events, conferences, and speaking engagements captioned live
• Phone calls, meetings, and training sessions transcribed instantly
• Speeches, announcements, and briefing transcribed on-location

Applications of Real-Time Speech Recognition Technology

Beyond the immediate implications of captions and transcriptions in real-time, your business can benefit from integrating our voice-to-text services for advanced business applications (examples below).

• Communication access for the deaf and hard-of-hearing for live media and events with easy-to-read transcripts and captions containing proper grammar, punctuation, and spelling.
• Monitor customer support call quality in real-time with artificial intelligence.
• Easily search through transcripts of your archived live content and find specific keywords with web-based transcript documents without having to listen through audio files.
• Advanced analytics and insights of spoken words for live content.
• Voice typing features in your software or dictation app
• Hands-free voice commands for your program or applications

Accurate Real-Time Speech-to-Text

Like our automated speech recognition services, the real-time captioning and transcription is powered by the same speech recognition engine that outperforms Google, Amazon, and Microsoft in our automatic speech recognition accuracy benchmarking tests.

“Since launching Rev.ai, we’ve prioritized delivering fast and accurate speech recognition for our customers through our unique API.”

Rev.ai is best-in-class for real-time speech-to-text accuracy. It’s powered by the same speech engine used by Rev automatic transcription, which had the lowest Word Error Rate (WER) of the competition in our recent benchmarking tests.

• 13.9% WER – Rev
• 15.1% WER – Google Speech-To-Text
• 18.0% WER – Amazon Transcribe
• 18.0% WER – Microsoft Azure Speech-to-Text

The real-time speech recognition offered by Rev.ai is able to understand a more complicated vocabulary, trained by our learning model based on a data set, which includes millions of hours of human-transcribed audio content. 

How Can I Get Real-Time Captioning and Transcription?

You can access the Rev.ai API to get started with real-time captions and transcription. The API comes with software development kits (SDKs), comprehensive documentation, and expert support.

Prices start at $0.035 per audio minute with no hidden fees.

Learn more about how Rev.ai’s real-time captioning and transcription can benefit your business.

Everybody’s Favorite Speech-to-Text Blog

We combine AI and a huge community of freelancers to make speech-to-text greatness every day. Wanna hear more about it?

Speech to Text - Voice Typing & Transcription

Take notes with your voice for free, or automatically transcribe audio & video recordings. secure, accurate & blazing fast..

~ Proudly serving millions of users since 2015 ~

I need to >

Dictate Notes

Start taking notes, on our online voice-enabled notepad right away, for free.

Transcribe Recordings

Automatically transcribe audios & videos - upload files from your device or link to an online resource (Drive, YouTube, TikTok and more).

Speechnotes is a reliable and secure web-based speech-to-text tool that enables you to quickly and accurately transcribe your audio and video recordings, as well as dictate your notes instead of typing, saving you time and effort. With features like voice commands for punctuation and formatting, automatic capitalization, and easy import/export options, Speechnotes provides an efficient and user-friendly dictation and transcription experience. Proudly serving millions of users since 2015, Speechnotes is the go-to tool for anyone who needs fast, accurate & private transcription. Our Portfolio of Complementary Speech-To-Text Tools Includes:

Voice typing - Chrome extension

Dictate instead of typing on any form & text-box across the web. Including on Gmail, and more.

Transcription API & webhooks

Speechnotes' API enables you to send us files via standard POST requests, and get the transcription results sent directly to your server.

Zapier integration

Combine the power of automatic transcriptions with Zapier's automatic processes. Serverless & codeless automation! Connect with your CRM, phone calls, Docs, email & more.

Android Speechnotes app

Speechnotes' notepad for Android, for notes taking on your mobile, battle tested with more than 5Million downloads. Rated 4.3+ ⭐

iOS TextHear app

TextHear for iOS, works great on iPhones, iPads & Macs. Designed specifically to help people with hearing impairment participate in conversations. Please note, this is a sister app - so it has its own pricing plan.

Audio & video converting tools

Tools developed for fast - batch conversions of audio files from one type to another and extracting audio only from videos for minimizing uploads.

Our Sister Apps for Text-To-Speech & Live Captioning

Complementary to Speechnotes

Reads out loud texts, files & web pages

Reads out loud texts, PDFs, e-books & websites for free

Speechlogger

Live Captioning & Translation

Live captions & translations for online meetings, webinars, and conferences.

Need Human Transcription? We Can Offer a 10% Discount Coupon

We do not provide human transcription services ourselves, but, we partnered with a UK company that does. Learn more on human transcription and the 10% discount .

Dictation Notepad

Start taking notes with your voice for free

Speech to Text online notepad. Professional, accurate & free speech recognizing text editor. Distraction-free, fast, easy to use web app for dictation & typing.

Speechnotes is a powerful speech-enabled online notepad, designed to empower your ideas by implementing a clean & efficient design, so you can focus on your thoughts. We strive to provide the best online dictation tool by engaging cutting-edge speech-recognition technology for the most accurate results technology can achieve today, together with incorporating built-in tools (automatic or manual) to increase users' efficiency, productivity and comfort. Works entirely online in your Chrome browser. No download, no install and even no registration needed, so you can start working right away.

Speechnotes is especially designed to provide you a distraction-free environment. Every note, starts with a new clear white paper, so to stimulate your mind with a clean fresh start. All other elements but the text itself are out of sight by fading out, so you can concentrate on the most important part - your own creativity. In addition to that, speaking instead of typing, enables you to think and speak it out fluently, uninterrupted, which again encourages creative, clear thinking. Fonts and colors all over the app were designed to be sharp and have excellent legibility characteristics.

Example use cases

• Voice typing
• Writing notes, thoughts
• Medical forms - dictate
• Transcribers (listen and dictate)

Transcription Service

Start transcribing

Fast turnaround - results within minutes. Includes timestamps, auto punctuation and subtitles at unbeatable price. Protects your privacy: no human in the loop, and (unlike many other vendors) we do NOT keep your audio. Pay per use, no recurring payments. Upload your files or transcribe directly from Google Drive, YouTube or any other online source. Simple. No download or install. Just send us the file and get the results in minutes.

• Transcribe interviews
• Captions for Youtubes & movies
• Auto-transcribe phone calls or voice messages
• Students - transcribe lectures
• Podcasters - enlarge your audience by turning your podcasts into textual content
• Text-index entire audio archives

Key Advantages

Speechnotes is powered by the leading most accurate speech recognition AI engines by Google & Microsoft. We always check - and make sure we still use the best. Accuracy in English is very good and can easily reach 95% accuracy for good quality dictation or recording.

Lightweight & fast

Both Speechnotes dictation & transcription are lightweight-online no install, work out of the box anywhere you are. Dictation works in real time. Transcription will get you results in a matter of minutes.

Super Private & Secure!

Super private - no human handles, sees or listens to your recordings! In addition, we take great measures to protect your privacy. For example, for transcribing your recordings - we pay Google's speech to text engines extra - just so they do not keep your audio for their own research purposes.

Health advantages

Typing may result in different types of Computer Related Repetitive Strain Injuries (RSI). Voice typing is one of the main recommended ways to minimize these risks, as it enables you to sit back comfortably, freeing your arms, hands, shoulders and back altogether.

Saves you time

Need to transcribe a recording? If it's an hour long, transcribing it yourself will take you about 6! hours of work. If you send it to a transcriber - you will get it back in days! Upload it to Speechnotes - it will take you less than a minute, and you will get the results in about 20 minutes to your email.

Saves you money

Speechnotes dictation notepad is completely free - with ads - or a small fee to get it ad-free. Speechnotes transcription is only $0.1/minute, which is X10 times cheaper than a human transcriber! We offer the best deal on the market - whether it's the free dictation notepad ot the pay-as-you-go transcription service.

Dictation - Free

• Online dictation notepad
• Voice typing Chrome extension

Dictation - Premium

• Premium online dictation notepad
• Premium voice typing Chrome extension
• Support from the development team

Transcription

$0.1 /minute.

• Pay as you go - no subscription
• Audio & video recordings
• Speaker diarization in English
• Generate captions .srt files
• REST API, webhooks & Zapier integration

Compare plans

Privacy policy.

We at Speechnotes, Speechlogger, TextHear, Speechkeys value your privacy, and that's why we do not store anything you say or type or in fact any other data about you - unless it is solely needed for the purpose of your operation. We don't share it with 3rd parties, other than Google / Microsoft for the speech-to-text engine.

Privacy - how are the recordings and results handled?

- transcription service.

Our transcription service is probably the most private and secure transcription service available.

• HIPAA compliant.
• No human in the loop. No passing your recording between PCs, emails, employees, etc.
• Secure encrypted communications (https) with and between our servers.
• Recordings are automatically deleted from our servers as soon as the transcription is done.
• Our contract with Google / Microsoft (our speech engines providers) prohibits them from keeping any audio or results.
• Transcription results are securely kept on our secure database. Only you have access to them - only if you sign in (or provide your secret credentials through the API)
• You may choose to delete the transcription results - once you do - no copy remains on our servers.

- Dictation notepad & extension

For dictation, the recording & recognition - is delegated to and done by the browser (Chrome / Edge) or operating system (Android). So, we never even have access to the recorded audio, and Edge's / Chrome's / Android's (depending the one you use) privacy policy apply here.

The results of the dictation are saved locally on your machine - via the browser's / app's local storage. It never gets to our servers. So, as long as your device is private - your notes are private.

Payments method privacy

The whole payments process is delegated to PayPal / Stripe / Google Pay / Play Store / App Store and secured by these providers. We never receive any of your credit card information.

More generic notes regarding our site, cookies, analytics, ads, etc.

• We may use Google Analytics on our site - which is a generic tool to track usage statistics.
• We use cookies - which means we save data on your browser to send to our servers when needed. This is used for instance to sign you in, and then keep you signed in.
• For the dictation tool - we use your browser's local storage to store your notes, so you can access them later.
• Non premium dictation tool serves ads by Google. Users may opt out of personalized advertising by visiting Ads Settings . Alternatively, users can opt out of a third-party vendor's use of cookies for personalized advertising by visiting https://youradchoices.com/
• In case you would like to upload files to Google Drive directly from Speechnotes - we'll ask for your permission to do so. We will use that permission for that purpose only - syncing your speech-notes to your Google Drive, per your request.

Speech to Text Converter

Descript instantly turns speech into text in real time. Just start recording and watch our AI speech recognition transcribe your voice—with 95% accuracy—into text that’s ready to edit or export.

How to automatically convert speech to text with Descript

Create a project in Descript, select record, and choose your microphone input to start a recording session. Or upload a voice file to convert the audio to text.

As you speak into your mic, Descript’s speech-to-text software turns what you say into text in real time. Don’t worry about filler words or mistakes; Descript makes it easy to find and remove those from both the generated text and recorded audio.

Enter Correct mode (press the C key) to edit, apply formatting, highlight sections, and leave comments on your speech-to-text transcript. Filler words will be highlighted, which you can remove by right clicking to remove some or all instances. When ready, export your text as HTML, Markdown, Plain text, Word file, or Rich Text format.

Download the app for free

More articles and resources.

New: Free Overdub on all Descript accounts, with easier voice cloning

What is a video crossfade effect?

New one-click integrations with Riverside, SquadCast, Restream, Captivate

Other tools from descript, business video maker, video brightness editor, youtube transcript generator, article to video, youtube description generator, split-screen video editor, social media video maker, video to text converter, podcast description generator.

Speech to Text

• 3 Create a new project Drag your file into the box above, or click Select file and import it from your computer or wherever it lives.

Expand Descript’s online voice recognition powers with an expandable transcription glossary to recognize hard-to-translate words like names and jargon.

Record yourself talking and turn it into text, audio, and video that’s ready to edit in Descript’s timeline. You can format, search, highlight, and other actions you’d perform in a Google Doc, while taking advantage of features like  text-to-speec h, captions, and more.

Go from speech to text in over 22 different languages, plus English. Transcribe audio in  French ,  Spanish , Italian, German and other languages from around the world. Finnish? Oh we’re just getting started.

Yes, basic real-time speech to text conversion is included for free with most modern devices (Android, Mac, etc.) Descript also offers a 95% accurate text-to-speech converter for up to 1 hour per month for free.

Speech-to-text conversion works by using AI and large quantities of diverse training data to recognize the acoustic qualities of specific words, despite the different speech patterns and accents people have, to generate it as text.

Yes! Descript‘s AI-powered Overdub feature lets you not only turn speech to text but also generate human-sounding speech from a script in your choice of AI stock voices.

Descript supports speech-to-text conversion in Catalan, Finnish, Lithuanian, Slovak, Croatian, French (FR), Malay, Slovenian, Czech, German, Norwegian, Spanish (US), Danish, Hungarian, Polish, Swedish, Dutch, Italian, Portuguese (BR), Turkish.

Descript’s included AI transcription offers up to 95% accurate speech to text generation. We also offer a white glove pay-per-word transcription service and 99% accuracy. Expanding your transcription glossary makes the automatic transcription more accurate over time.

Transcribe - Speech to Text ‪™‬ 4+

Voice recorder, notes, memos, hanna raita, designed for ipad.

• Offers In-App Purchases

Screenshots

Description.

The most professional speech-to-text transcriber! Meeting notes for Zoom, Google Meet, Microsoft Teams, and more. Stay connected and collaborative when you work from home. Thanks to our application you have the opportunity to record an important call or meeting, lecture or just save voice notes. Using incredible AI technology our app instantly transcribes from voice to text. Top features: - LIVE HIGH-QUALITY VOICE TRANSCRIPTION Using AI we perform speech-to-text conversion very quickly and accurately. Our accuracy is many times higher than our competitors thanks to our advanced technology. - SUPPORTS ALL POPULAR LANGUAGES Recognition accuracy is high in any available language. The smart system will try to match the language you speak as soon as you install the app, but if you need a different language, just go to the settings and change it! - ADVANCED EXPORT Export the file in the format you prefer, whether it's a text version of the file or an audio one - SMART SEARCH Do you want to quickly find a file or words in an audio recording? Intelligent search makes it much easier to do so. Search files, text notes, audio notes and more - CLEVER COPY & SHARE Copy and share only those blocks of text or audio that are necessary.Now you don't have to share the whole file to show a person a part of an audio or text file. - OFFLINE ACCESS TO UNLIMITED LIBRARY No internet access? Not a problem. You always have the audio and text version of the file you need at your fingertips. - NO ADS We respect our users, so our app will not contain ads ever! For a better acquaintance with our application we offer a FREE trial period, which you CAN CANCEL at any time in the settings. If you choose to get one of our plans, your payment will be charged to your iTunes Account at confirmation of purchase. Subscription automatically renews unless auto-renew is turned off at least 24-hours before the end of the current period. The cost of the renewal depends on your Subscription Plan. Subscriptions may be managed by the user and auto-renewal may be turned off by going to the user's Account Settings after purchase. When canceling a subscription, your subscription will remain active until the end of the period. Auto-renewal will be disabled, but the current subscription will not be refunded. Thousands of users trust us, and we value each of them. Our support works 0-24, try our app and write an honest review to support. This is the biggest user gratitude for us. Questions? Contact us at - [email protected] Term of use: - https://sites.google.com/view/hey-transcribe-terms Privacy policy: - https://sites.google.com/view/hey-transcribe-privacy

Subscriptions

App privacy.

The developer, Hanna Raita , indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy .

Data Not Linked to You

The following data may be collected but it is not linked to your identity:

• Identifiers
• Diagnostics

Privacy practices may vary, for example, based on the features you use or your age. Learn More

Information

English, French, German, Italian, Japanese, Korean, Portuguese, Russian, Simplified Chinese, Spanish, Traditional Chinese, Vietnamese

• Dictation to text $7.99
• Dictation to text $39.99
• Powered by Otter AI $5.99
• Voice memos $4.99
• Speech to text $44.99
• Developer Website
• App Support
• Privacy Policy

More By This Developer

Translator – translate voice

You Might Also Like

VoicePen: AI Speech to Text

Voice to Text AI

TrainDesign

CyberTracker

Time : Calculator++

SpeakApp AI: Voice Notes

• Español – América Latina
• Português – Brasil
• Cloud Speech-to-Text
• Documentation

Transcribe streaming audio from a microphone

Transcribe streaming audio from a microphone.

Explore further

For detailed documentation that includes this code sample, see the following:

• Transcribe audio from streaming input

Code sample

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries . For more information, see the Speech-to-Text Go API reference documentation .

To authenticate to Speech-to-Text, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries . For more information, see the Speech-to-Text Java API reference documentation .

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries . For more information, see the Speech-to-Text Node.js API reference documentation .

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries . For more information, see the Speech-to-Text Python API reference documentation .

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser .

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License , and code samples are licensed under the Apache 2.0 License . For details, see the Google Developers Site Policies . Java is a registered trademark of Oracle and/or its affiliates.

Create a free profile to get unlimited access to exclusive videos, sweepstakes, and more!

Kyle Richards Reveals the Text She Sent to Dorit Kemsley After the Reunion: "I'm Shocked"

After The Real Housewives of Beverly Hills Season 13 reunion, Kyle called Dorit out for sharing their private texts. 

In addition to navigating the end of her marriage to Mauricio Umansky on  The Real Housewives of Beverly Hills   Season 13 , Kyle Richards lost another relationship during the season: her friendship with Dorit Kemsley . 

How to Watch

Watch The Real Housewives of Beverly Hills  on  Peacock  and the Bravo App .

In the closing moments of the Season 13 finale , it was revealed that Kyle and Dorit hadn't spoken in months , and the ladies were face-to-face for the first time at the reunion. 

Backstage at the reunion, Dorit shared a text message that she received from Kyle to Erika Jayne . The moment upset Kyle, and she just revealed that she actually contacted Dorit after the reunion wrapped. 

Kyle Richards' Text to Dorit Kemsley After the RHOBH Season 13 Reunion

After finding out that Dorit publicly shared the private text message that Kyle sent her ahead of the reunion, Kyle confronted her in a new message. "I sent her a text saying I am, 'Wow, I'm shocked that you would do that,'" Kyle said on Let's Talk with Kelly Ripa . "Never in 13 years, I’ve never had, even the worst of worst situations, I’ve never had someone do that to me."

Here's What You May Have Missed on Bravo:

Kyle Richards Shares Big News on Her and Mauricio's Separation Status: "To Be Honest..."

Dorit Kemsley Still Has Feelings About Kyle Richards' Tattoos

Why Dorit Kemsley Is Questioning Kyle and Morgan’s "Really, Really Close Friendship"

Did Dorit respond to Kyle's message? Kyle said no.

"I didn’t even get a cricket emoji," Kyle added on the podcast. "Nothing.”

Dorit Kemsley Reveals If She Would Be Friends with Kyle Richards Again

Though Dorit didn't respond to Kyle's post-reunion text (at least, according to Kyle), the Beverly Beach founder is open to repairing their friendship . 

Read the Lengthy Text Kyle Richards Sent Dorit Kemsley Before the Reunion: "So Manipulated, So Calculated"

“I would like for Kyle and I to sit down but have a genuine honest open conversation," Dorit said when she appeared on The Skinny Confidential: Him and Her podcast. "There’s a lot of hurt."

Stream The Real Housewives of Beverly Hills on Peacock now. 

• Dorit Kemsley
• Kyle Richards

The Real Housewives of Beverly Hills

• Relationships

Related Stories

Inside Gretchen and Slade's Anniversary Celebration

Lala Kent Questions Ariana Madix Post-Breakup Decisions

Brittany Shares Update on Her Son Amid Split from Jax

Bria Gives Ominous Hint About Mariah's Arrival

Gizelle Dishes on Jason Relationship & Who Else She's Dating

Why Chris Bassett Was Missing for Most of RHOP Season 8

Everett and His Wife Are Expecting Their First Child

Go Inside Tom and Victoria's Night Out with JoJo Siwa (PICS)

Tom Embarks on a Hawaiian Vacation with GF Sophia (PICS)

Brittany Cartwright Calls Jax a "Toddler" Amid Their Split

Amanda Shares Why She's *Really* "Harsh" with Kyle

What's Next For Ariana Madix After Chicago Wraps

Latest Videos

Kyle Richards on Why She Filmed That Music Video with Morgan Wade

Start Watching Part 3 of The Real Housewives of Beverly Hills Season 13 Reunion

Sutton Stracke Says She "Got a Spanking" for Suggesting PK Might Have Cheated

Recommended for you.

We Have a Major Update on Tom, Katie, and Katie

Kyle Says She Will Spend Christmas with Mauricio

Kim Richards Just Shocked Kyle with a New Update

Israel-Gaza latest: Israel withdraws almost all ground troops from southern Gaza; Iran issues threat to Israeli embassies

Today marks six months since the 7 October attacks by Hamas that left more than 1,100 Israelis dead and prompted Israel's ongoing military operation in Gaza, which has killed more than 33,000 people. We'll be bringing you updates on this throughout the day.

Sunday 7 April 2024 12:56, UK

• Israel-Hamas war

Please use Chrome browser for a more accessible video player

• Israeli military withdraws almost all ground troops from southern Gaza
• Today marks six months since the 7 October attacks
• Iranian official says Israeli embassies are no longer safe
• Israel 'absolutely' committed to ground invasion of Rafah
• Hostage's body recovered by Israeli military
• Podcast: Should the UK stop selling arms to Israel?
• Live reporting by Josephine Franks

Israeli prime minister Benjamin Netanyahu has said Israel is ready to reach a deal to secure the release of 130 hostages held by Hamas. 

But he said Israel would not give in to the "extreme" demands of Hamas. 

Talks aimed at securing a ceasefire and the release of hostages are due to take place in Cairo today. 

Mr Netanyahu said Hamas hoped international pressure would make Israel give in to its demands, but he stressed that would not happen. 

The UK would not export arms to Israel if doing so was found to be in breach of international law, Oliver Dowden has suggested.

Speaking on the BBC's Sunday With Laura Kuenssberg, the deputy prime minister said the UK would not "supply those arms" if it was unable to legally do so.

It comes amid mounting pressure on ministers to reveal what legal advice they have received on continuing arms exports to Israel.

This morning, Mr Dowden told Sky News the UK has "one of the toughest arms export control [regimes] in the world" and said there had been no change to the legal advice. 

Families of hostages taken by Hamas reflect on the day they went missing and the six months since, in a video shared by the Foreign Office. 

Iran's semi-official ISNA news agency has published a graphic showcasing what it said were nine different types of Iranian missiles capable of reaching Israel. 

Tensions appear to be ratcheting up between the two sides, and a short while ago an Iranian official warned that no Israeli embassy is safe. 

US officials said on Friday that they were on high alert about the possibility of a significant Iranian strike on targets inside Israel. 

Iran has blamed Israel for a deadly attack on the Iranian consulate Damascus, Syria, last week that killed at least seven officials. 

Among those killed was atop commander in Iran's elite Revolutionary Guards (IRGC). 

Satellite imagery reveals the extent of the destruction at Gaza's al Shifa hospital after six months of war. 

These images collected by Maxar show the hospital in June 2022, long before the war began, compared with earlier this week. 

Israel withdrew its troops from the hospital on Monday after a two-week raid, leaving behind destroyed buildings and dead bodies. 

A senior Iranian official says none of Israel's embassies are safe any more, after a suspected Israeli strike on the Iranian consulate in Damascus.

Twenty-eight Israeli embassies around the world temporarily closed on Friday due to fears of reprisal from Iran, the official said. 

Yahya Rahim Safavi, an adviser to the Supreme Leader, said the attack was a "violation of international laws".

Seven members of Iran's Revolutionary Guard were killed in the 1 April attack, with Iran vowing retaliation. 

With ceasefire talks due to begin today in Cairo, Sky News spoke to Israeli government spokesperson Avi Hyman.

Despite an announcement this morning Israel has withdrawn almost all ground troops from southern Gaza, Mr Hyman said Benjamin Netanyahu would "absolutely" go ahead with a ground invasion of Rafah.

"If we don't go ahead with Rafah, we lose the war."

He said Israel was "ploughing ahead" with its aims to destroy Hamas, bring the remaining hostages home and "ensure that Gaza doesn't pose a threat to us".

Asked what the point was in joining ceasefire talks when Israel was committed to a ground invasion, he said: "We will do our absolute utmost to ensure that we keep up maximum military pressure against Hamas and we keep all the diplomatic channels open.

"Because remember, we freed about half of the hostages using that formula."

Incoming Irish prime minister Simon Harris tells Sky News what has happened in Gaza is "utterly reprehensible". 

He tells our  senior Ireland correspondent David Blevins : "It's appalling and it's grotesque.

"And we are seeing children being maimed and killed - innocent children. It is disgusting. It is despicable. And it must stop."

He says Ireland "will always speak truth to power", and calls for "an immediate ceasefire".

"The attack on aid workers was particularly, in my view, callous and chilling, and we will continue to call that out.

"We also, as a country, stand ready to play our part in a political process that brings about a two-state solution."

He adds: "This country, and indeed the UK, know a lot about the importance of peace processes.

"This ultimately requires a political solution that delivers a two-state solution."

The Hamas-run Gaza health ministry has released its updated figures for the number of Palestinians killed and wounded in six months of war. 

It says 33,175 people have been killed and 75,886 injured.

Boaz Bismuth, member of the Israeli Knesset (parliament) in Benjamin Netanyahu's party, has defended how Israel has managed the flow of humanitarian aid into Gaza. 

He tells Sky News aid is entering Gaza, but that the Israeli hostages held by Hamas have not seen doctors or the Red Cross, as "we don't know if they're alive or dead".

"We speak a lot of humanitarian [aid] in Gaza, forgetting humanitarian [aid for] our own people."

Challenged by Trevor Phillips on Israel's conduct, he says Israel allowed humanitarian aid "from day one" and that it respects international law.

He says Israel has allowed aid from air, land, and sea, and has opened up new aid corridors when asked by the international community.

"We are at war against terrorists. We're not at war against [the] civilian population," he declares.

Be the first to get Breaking News

Install the Sky News app for free