This browser is no longer supported.
Upgrade to Microsoft Edge to take advantage of the latest features, security updates, and technical support.
Text to speech REST API
- 3 contributors
The Speech service allows you to convert text into synthesized speech and get a list of supported voices for a region by using a REST API. In this article, you learn about authorization options, query options, how to structure a request, and how to interpret a response.
Use cases for the text to speech REST API are limited. Use it only in cases where you can't use the Speech SDK . For example, with the Speech SDK you can subscribe to events for more insights about the text to speech processing and results.
The text to speech REST API supports neural text to speech voices in many locales. Each available endpoint is associated with a region. A Speech resource key for the endpoint or region that you plan to use is required. Here are links to more information:
- For a complete list of voices, see Language and voice support for the Speech service .
- For information about regional availability, see Speech service supported regions .
- For Azure Government and Microsoft Azure operated by 21Vianet endpoints, see this article about sovereign clouds .
Costs vary for prebuilt neural voices (called Neural on the pricing page) and custom neural voices (called Custom Neural on the pricing page). For more information, see Speech service pricing .
Before you use the text to speech REST API, understand that you need to complete a token exchange as part of authentication to access the service. For more information, see Authentication .
Get a list of voices
You can use the tts.speech.microsoft.com/cognitiveservices/voices/list endpoint to get a full list of voices for a specific region or endpoint. Prefix the voices list endpoint with a region to get a list of voices for that region. For example, to get a list of voices for the westus region, use the https://westus.tts.speech.microsoft.com/cognitiveservices/voices/list endpoint. For a list of all supported regions, see the regions documentation.
Voices and styles in preview are only available in three service regions: East US, West Europe, and Southeast Asia.
Request headers
This table lists required and optional headers for text to speech requests:
Request body
A body isn't required for GET requests to this endpoint.
Sample request
This request requires only an authorization header:
Here's an example curl command:
Sample response
You should receive a response with a JSON body that includes all supported locales, voices, gender, styles, and other details. The WordsPerMinute property for each voice can be used to estimate the length of the output speech. This JSON example shows partial results to illustrate the structure of a response:
HTTP status codes
The HTTP status code for each response indicates success or common errors.
Convert text to speech
The cognitiveservices/v1 endpoint allows you to convert text to speech by using Speech Synthesis Markup Language (SSML) .
Regions and endpoints
These regions are supported for text to speech through the REST API. Be sure to select the endpoint that matches your Speech resource region.
Prebuilt neural voices
Use this table to determine availability of neural voices by region or endpoint:
Voices in preview are available in only these three regions: East US, West Europe, and Southeast Asia.
Custom neural voices
If you've created a custom neural voice font, use the endpoint that you've created. You can also use the following endpoints. Replace {deploymentId} with the deployment ID for your neural voice model.
The preceding regions are available for neural voice model hosting and real-time synthesis. Custom neural voice training is only available in some regions. But users can easily copy a neural voice model from these regions to other regions in the preceding list.
Long Audio API
The Long Audio API is available in multiple regions with unique endpoints:
If you're using a custom neural voice, the body of a request can be sent as plain text (ASCII or UTF-8). Otherwise, the body of each POST request is sent as SSML . SSML allows you to choose the voice and language of the synthesized speech that the text to speech feature returns. For a complete list of supported voices, see Language and voice support for the Speech service .
This HTTP request uses SSML to specify the voice and language. If the body length is long, and the resulting audio exceeds 10 minutes, it's truncated to 10 minutes. In other words, the audio length can't exceed 10 minutes.
* For the Content-Length, you should use your own content length. In most cases, this value is calculated automatically.
The HTTP status code for each response indicates success or common errors:
If the HTTP status is 200 OK , the body of the response contains an audio file in the requested format. This file can be played as it's transferred, saved to a buffer, or saved to a file.
Audio outputs
The supported streaming and nonstreaming audio formats are sent in each request as the X-Microsoft-OutputFormat header. Each format incorporates a bit rate and encoding type. The Speech service supports 48-kHz, 24-kHz, 16-kHz, and 8-kHz audio outputs. Each prebuilt neural voice model is available at 24kHz and high-fidelity 48kHz.
- NonStreaming
If you select 48kHz output format, the high-fidelity voice model with 48kHz will be invoked accordingly. The sample rates other than 24kHz and 48kHz can be obtained through upsampling or downsampling when synthesizing, for example, 44.1kHz is downsampled from 48kHz.
If your selected voice and output format have different bit rates, the audio is resampled as necessary. You can decode the ogg-24khz-16bit-mono-opus format by using the Opus codec .
Authentication
Each request requires an authorization header. This table illustrates which headers are supported for each feature:
When you're using the Ocp-Apim-Subscription-Key header, only your resource key must be provided. For example:
When you're using the Authorization: Bearer header, you need to make a request to the issueToken endpoint. In this request, you exchange your resource key for an access token that's valid for 10 minutes.
Another option is to use Microsoft Entra authentication that also uses the Authorization: Bearer header, but with a token issued via Microsoft Entra ID. See Use Microsoft Entra authentication .
How to get an access token
To get an access token, you need to make a request to the issueToken endpoint by using Ocp-Apim-Subscription-Key and your resource key.
The issueToken endpoint has this format:
Replace <REGION_IDENTIFIER> with the identifier that matches the region of your subscription.
Use the following samples to create your access token request.
HTTP sample
This example is a simple HTTP request to get a token. Replace YOUR_SUBSCRIPTION_KEY with your resource key for the Speech service. If your subscription isn't in the West US region, replace the Host header with your region's host name.
The body of the response contains the access token in JSON Web Token (JWT) format.
PowerShell sample
This example is a simple PowerShell script to get an access token. Replace YOUR_SUBSCRIPTION_KEY with your resource key for the Speech service. Make sure to use the correct endpoint for the region that matches your subscription. This example is currently set to West US.
cURL sample
cURL is a command-line tool available in Linux (and in the Windows Subsystem for Linux). This cURL command illustrates how to get an access token. Replace YOUR_SUBSCRIPTION_KEY with your resource key for the Speech service. Make sure to use the correct endpoint for the region that matches your subscription. This example is currently set to West US.
This C# class illustrates how to get an access token. Pass your resource key for the Speech service when you instantiate the class. If your subscription isn't in the West US region, change the value of FetchTokenUri to match the region for your subscription.
Python sample
How to use an access token.
The access token should be sent to the service as the Authorization: Bearer <TOKEN> header. Each access token is valid for 10 minutes. You can get a new token at any time, but to minimize network traffic and latency, we recommend using the same token for nine minutes.
Here's a sample HTTP request to the Speech to text REST API for short audio:
Use Microsoft Entra authentication
To use Microsoft Entra authentication with the Speech to text REST API for short audio, you need to create an access token. The steps to obtain the access token consisting of Resource ID and Microsoft Entra access token are the same as when using the Speech SDK. Follow the steps here Use Microsoft Entra authentication
- Create a Speech resource
- Configure the Speech resource for Microsoft Entra authentication
- Get a Microsoft Entra access token
- Get the Speech resource ID
After the resource ID and the Microsoft Entra access token were obtained, the actual access token can be constructed following this format:
You need to include the "aad#" prefix and the "#" (hash) separator between resource ID and the access token.
To learn more about Microsoft Entra access tokens, including token lifetime, visit Access tokens in the Microsoft identity platform .
- Create a free Azure account
- Get started with custom neural voice
- Batch synthesis
Was this page helpful?
Additional resources
Best Open Source Text-to-Speech API Free and yet, High-Quality Looking for the best best open source text to speech api free you can try today? We’ve listed them all here with features so you can compare.
By --> conradical --> in API
Share this post
Low latency, highest quality text to speech API
Table of contents.
In a world where engaging audio is paramount, open-source text-to-speech (TTS) APIs offer incredible functionality, from voiceovers for videos to real-time voice generation in interactive AI apps. Here’s a dive into the best TTS APIs that allow developers to work on customization, support different languages like English, French, and German, and provide high-quality speech output for various use cases.
Coqui TTS: Deep Learning Meets Text-to-Speech
Coqui TTS is an open-source gem for creating high-quality speech synthesis systems. Leveraging deep learning and **real-time** speech synthesis, Coqui delivers natural-sounding speech across multiple languages. It’s multilingual, covering diverse datasets to ensure speech generation that meets industry standards for quality and customization.
Key Features :
- Customizable TTS models for different languages
- Supports Python and other programming languages
- Low latency in speech output
Mozilla TTS: The Pioneer of Open-Source TTS API
Mozilla TTS, known for its advanced speech synthesis and deep neural network models, is a robust choice for developers needing flexibility. With real-time response, Mozilla TTS works on Linux, Windows, and macOS, making it suitable for cross-platform apps.
Notable Aspects :
- Comprehensive language support including English, Russian, and more
- Open access to Github for TTS fine-tuning and voice cloning
- Powerful for both audiobooks and voiceovers
eSpeak: Lightweight Text-to-Speech Engine
If you’re looking for something lighter and faster, eSpeak fits the bill. This open-source TTS engine is efficient for converting text into audio files without heavy machine learning dependencies. eSpeak is also known for its cost-effective solution in voice synthesis for straightforward applications.
- Supports Python and easy integration into Java
- Wide range of language support
- Real-time text-to-speech with a minimalistic approach
MaryTTS: Java-Based Text-to-Speech API
For developers working in Java, MaryTTS is one of the best open-source TTS options. Originating from Germany, MaryTTS supports multiple languages and offers a **high-quality** voice generator for multilingual support. MaryTTS’s docs are also very user-friendly, which is a bonus for those new to text-to-speech technology.
Core Attributes :
- Smooth speech synthesis with SSML support
- Ideal for creating voice assistants and chatbots
- Reliable API structure on a well-maintained Github repository
Get Started with the Lowest Latency Text to Speech API
Unlock the power of seamless voice generation with PlayHT’s text to speech API , featuring the lowest latency in the industry. Enhance your applications with high-quality, natural-sounding AI voices and deliver an exceptional user experience – in real time.
Try Playground Get Started
ElevenLabs: Premium AI Voice Solution
For high-end, AI voice quality, ElevenLabs provides cutting-edge TTS models powered by artificial intelligence. Although not entirely open-source, they offer a free trial with a variety of real-time applications. This API is top-notch for voiceovers, ensuring a natural-sounding speech experience.
Highlights :
- Advanced speech recognition with transcription features
- Works across Windows and Linux
- Perfect for voice cloning and other intricate speech output needs
Google Cloud and Amazon Polly: Robust TTS APIs with Free Tiers
Both Google Cloud Text-to-Speech and Amazon Polly offer open-source text-to-speech engines with limited free tiers. While not entirely open-source, they give access to **cutting-edge** text-to-speech technology and AI voice options. They support customization for various use cases, from audiobooks to voice assistants.
Key Advantages :
- Excellent for multilingual support with French, German, and other languages
- Integrated machine learning features for speech recognition and transcription
- High latency tolerance and fast real-time TTS API responses
Other Text to Speech APIs that are Free
For developers and businesses exploring best text-to-speech tools, TTS APIs have transformed audio applications, from mobile Android apps to LLM-based voice experiences. Here’s a guide to the top three text-to-speech API providers, showcasing PlayHT as the leading option.
PlayHT: The Best Text-to-Speech API for Real-Time, Natural Audio
PlayHT tops the list for its **cutting-edge** text-to-speech models that deliver ultra-realistic synthesizer output, making it ideal for content creators, voiceovers, and live interactions. PlayHT leverages AI and advanced text-to-speech models to produce natural-sounding voices with near-zero latency. It’s the perfect solution for creators looking for a seamless, high-quality audio experience across Android, web, and desktop applications.
- Real-time response with incredibly low latency, suitable for interactive applications
- Works across platforms, including Android and Windows
- Supports WAV and other audio formats for flexible output
- API can create tailored text-to-speech models for specific use cases
Why Choose PlayHT?
With PlayHT, you get the industry’s best combination of LLM technology and text-to-speech. It stands out for applications needing responsive and immersive AI voices, from live narration to on-demand audio.
IBM Watson TTS: Reliable and Feature-Rich
IBM’s Watson TTS API brings robust text-to-speech solutions, offering customization and advanced synthesizer functionality that suit various use cases, such as voice assistants and automated customer service. IBM Watson’s LLM framework is designed to produce clear, intelligible speech synthesis and supports multiple audio output formats, including WAV.
- Integrates well with IBM’s full suite of AI solutions
- Multilingual support for diverse applications and regions
- Strong reputation for stability and reliable API integration
IBM Watson in Action
From voice assistants to interactive kiosks, IBM Watson TTS is known for delivering consistent and accurate speech synthesis, making it a go-to for many enterprise applications.
Microsoft Azure TTS: AI-Powered Versatility
Microsoft Azure’s text-to-speech API offers customizable, AI-driven voices, perfect for developers looking to integrate synthesizer models into Android and web apps. The text-to-speech models in Microsoft Azure include natural-sounding voices that excel in real-time applications and voiceovers, leveraging advanced AI to adapt to various use cases.
- OpenAI integration for enhanced voice generation
- Supports custom text-to-speech models for specific requirements
- Multilingual with flexible audio format support, including WAV
Microsoft Azure in Context
A top choice for businesses needing flexible and scalable text-to-speech solutions, Azure TTS can create interactive and personalized AI voice experiences, thanks to its seamless integration with other Microsoft and OpenAI services.
Choosing the Right Open-Source TTS Engine for Your Project
When it comes to specific needs in TTS, consider factors like real-time response, language support, and platform compatibility (**Windows**, Linux, macOS). For a flexible, customizable solution, Coqui and Mozilla TTS excel with their open-source TTS models and voice generation capabilities, while MaryTTS is unbeatable for Java applications.
In an era where voice assistants, chatbots, and audiobooks demand top-notch audio, open-source text-to-speech APIs remain the best solution for developers who need cost-effective, versatile TTS options without sacrificing audio quality.
Quick Tip: Interested in the fastest, most natural-sounding TTS solution for your projects? Try the PlayHT text-to-speech API for seamless, ultra-low latency audio in real-time.
Whether you’re streaming live or generating voiceovers, PlayHT delivers every word clearly and smoothly.
Recent Posts
Generative AI for Enterprises: The Ultimate Guide
The Best Text to Speech APIs
Best AI Voice Generators You Should Check Out
Best AI Content Generators that are all the Rage Right Now
AI Text to Speech Voice Cloning
How to Clone Your Voice with AI
AI Voice Over Tips and Tricks to Up Your Game
How to Choose the Best IVR Voice
What Is On-Premise Text To Speech API?
Voice Cloning Tips for the Best Quality
IVR Design Guide for Delightful Customer Experiences
Play.ht Launches Multilingual Synthesis and Cross-Language Voice Cloning
AI in the Workplace: Transforming & Improving Processes
Best IVR for Small Business
Streamline Your Call Management with a Custom IVR Script
AI in Education: Its Present and Its Future
Best AI Agents You Should Know
The Only Text to Speech Guide You’ll Ever Need
4 Benefits of Voice Synthesis for YouTube Content Creators
eLearning Voice Over: A Comprehensive Guide
Introducing peregrine: text to speech model with emotion and laughter.
Add AI Voice to Your Presentations
Different text to speech speaking styles now on play.ht, best text to speech english voices.
Chatbots VS Conversational AI
How to add Text to Speech Audio to your WordPress Blog posts.
iMovie Voiceover With Text to Speech Voices
AI Voices – The Future Of Voiceover Audio
How To Upload Podcasts To Apple
Amazon Polly VS Google Wavenet Text to Speech
Are Audio Articles the next norm in content marketing?
Will AI Replace Voice Actors
Can artificial voices be the next tool in a content-marketers toolbelt?
Could this be the most realistic synthetic voice.
How to Do TikTok Text To Speech? (With Examples)
YouTube Text to Speech : Top Recommendations
What are Phonemes? What’s Their Role in TTS Pronunciation?
The ultimate guide to setup twitch tts (text to speech).
The Ultimate Guide to Use Discord TTS (Text to Speech)
Deepfake AI Voice : Top Software Recommendations
Best voice changer for ps4/ps5 right now, the best voice changer for xbox.
Best Free Text to Speech Software Right Now
The Best AI Voice Cloning Software Right Now!
Best voice changer for discord you should try out, top 10 best text to speech apps, the best speech to text chrome extensions right now, how to convert pdf text to speech, how to convert text to speech on a macbook, setting the tone: crafting narrator scripts that resonate, listen & rate tts voices, top ai apps.
Voiceplug AI
VoiceNation
NaturalReader
Cartesia AI
LexReception
Voice Dream
Google Text to Speech
Answering.ai
Alternatives
Best Hyperbound Alternatives
Best AnswerConnect Alternatives
Best Goodcall Alternatives
Best Talkie.AI Alternatives
Best Deepgram Alternatives
Best WellSaid Labs Alternatives
Best Dialzara Alternatives
Best Amazon Polly Alternatives
Best Tenyx Alternatives
Best Perplexity AI Alternatives
Best Cartesia AI Alternatives
Best Uberduck Alternatives
Best LexReception Alternatives
Best Arini.AI Alternatives
Best Lovo Alternatives
Best Listnr AI Alternatives
Best Baby AGI Alternatives
Best Typecast Alternatives
Best NaturalReader Alternatives
Best Agent GPT Alternatives
Best AutoGPT AI Alternatives
Best DialogFlow Alternatives
Best Bland.AI Alternatives
Best Synthesia Alternatives
Best Google Text to Speech Alternatives
Best Voiceflow Alternatives
Best E42 Alternatives
Best Phonely.AI Alternatives
Best Wavel AI Alternatives
Best Vocode Alternatives
Similar articles
Free Text to Speech API: High-Quality, AI-Powered Speech Synthesis
Google Text to Speech API: A Step-by-Step Tutorial with Examples
How to Decrease Latency in Text to Speech APIs
Best Text to Speech SDKs for High-Quality Voice Generation
Best Free Text-to-Speech APIs to Test
Deepgram Text-to-Speech SDK: A Complete Guide
Best Text to Speech JavaScript APIs
Websockets vs REST API vs API: Choosing the Right Communication Protocol for Your Web Application
Best TTS API: Top Choices and Must-Have Features for High-Quality Audio
Google Text to Speech Latency: Benchmarks, Comparisons, and Testing
Best Text to Speech Python APIs
Speechify Text to Speech Latency: A Speed Guide
Deepgram Text to Speech API JavaScript: A Comprehensive Guide
Text to Speech WebSockets: Real-Time TTS
SDK vs API: What’s the Difference?
Amazon Text-to-Speech Latency: Optimizing Response Times with Amazon Polly
Try the best text to speech api for free.
IMAGES
VIDEO
COMMENTS
6. After the new language is installed, navigate to Language and find it in your Preferred languages list. Select your language and choose Options to adjust other language settings, download features, etc.. Speech settings and voices. If text-to-speech is available in your language, you can adjust voice settings to change reader voices and speeds when using audible features like Read Aloud in ...
Customize speech in your app for your domain—including OpenAI Whisper model—or give your copilot a branded voice. Enable real-time, multi-language speech to speech translation and speech to text transcription of audio streams. Run AI models wherever your data resides. Deploy your apps in the cloud or at the edge with containers.
Microsoft offers over 400 neural voices covering more than 140 languages and locales. With these Text-to-Speech voices, you can quickly add read-aloud functionality for a more accessible app design or give a voice to chatbots to provide a richer conversational experience to your users.
Feature Summary Demo; Prebuilt neural voice (called Neural on the pricing page): Highly natural out-of-the-box voices. Create an Azure subscription and Speech resource, and then use the Speech SDK or visit the Speech Studio portal and select prebuilt neural voices to get started. Check the pricing details.: Check the Voice Gallery and determine the right voice for your business needs.
To explore these new capabilities, simply sign up for the Speech service on Azure and access the Speech Studio Voice Gallery. Microsoft provides a wide range of neural voices, offering over 400 options in more than 140 languages and locales. These text-to-speech voices enable you to quickly integrate read-aloud functionality into your ...
With Azure AI Speech, you can run an application that synthesizes a human-like voice to read text. You can change the voice, enter text to be spoken, and listen to the output on your computer's speaker. Tip. You can try text to speech in the Speech Studio Voice Gallery without signing up or writing any code. Tip.
Microsoft offers over 400 neural voices covering more than 140 languages and locales. With these Text-to-Speech voices, you can quickly add read-aloud functionality for a more accessible app design or give a voice to chatbots to provide a richer conversational experience to your users.
Related content. Like Azure AI Speech voices, OpenAI text to speech voices deliver high-quality speech synthesis to convert written text into natural sounding spoken audio. This unlocks a wide range of possibilities for immersive and interactive user experiences. OpenAI text to speech voices are available via two model variants: Neural and ...
Build apps and services that speak naturally with more than 400 voices across 140 languages and dialects. Create a customized voice to differentiate your brand and use various speaking styles to bring a sense of emotion to your spoken content. Learn more about text to speech. Voice Gallery. Browse expressive voices with humanlike speech to find ...
The primary objective of neural text to speech HD voices is to generate high-fidelity audio. The synthetic speech produced by our system can closely mimic human speech in both quality and naturalness. With neural text to speech HD voices, we release different versions of the same voice, each with a unique base model size and recipe.
Microsoft offers over 400 neural voices covering more than 140 languages and locales. With these Text-to-Speech voices, you can quickly add read-aloud functionality for a more accessible app design or give a voice to chatbots to provide a richer conversational experience to your users.
Discover the full list of supported languages for Neural Text to Speech, in addition to Microsoft Edge Read aloud. 36 new voices are in preview for some popular languages. For each languages' prebuilt voice, we have provided one female and one male voice. However, in the real world, there are scenarios that require one or more voices to ...
Neural text to speech (Neural TTS) is a powerful speech synthesis capability of Azure cognitive services. It enables users to convert text to lifelike speech, and can be used in various scenarios including voice assistant, content read-aloud capabilities, accessibility tools, etc. Neural TTS has been incorporated into Microsoft's flagship ...
Build voice-enabled generative AI apps confidently and quickly with the Azure AI Speech. Transcribe speech to text with high accuracy, produce natural-sounding text-to-speech voices, translate spoken audio, and use speaker recognition during conversations. Build faster with pre-built and customizable AI models in Azure AI Studio.
Azure Neural Text-to-Speech (Neural TTS) is a powerful AIGC (AI Generated Content) service that allows users to turn text into lifelike speech. It has been applied to a wide range of scenarios, including voice assistants, content read-aloud capabilities, and accessibility uses. During the past months, Azure Neural TTS has achieved parity with ...
Azure Neural Text to Speech (TTS), a powerful speech synthesis capability of Azure Cognitive Services, enables developers to convert text to lifelike speech using AI. Enterprises and agencies utilize Azure Neural TTS for video game characters, chatbots, content readers, and more. The Azure TTS product team is continuously working on bringing new voice styles and emotions to the US market and ...
Select synthesis language and voice. The text to speech feature in the Speech service supports more than 400 voices and more than 140 languages and variants. You can get the full list or try them in the Voice Gallery. Specify the language or voice of SpeechConfig to match your input text and use the specified voice.
You can add the Speak command to your Quick Access Toolbar by doing the following in Word, Outlook, PowerPoint, and OneNote: Next to the Quick Access Toolbar, click Customize Quick Access Toolbar. Click More Commands. In the Choose commands from list, select All Commands. Scroll down to the Speak command, select it, and then click Add.
This will take you to the Speech settings page. Under Manage voices, select Add voices. Select the language you would like to install voices for and select Add. The new voices will download and be ready for use in a few minutes, depending on your internet download speed. Once the voices for the new languages are downloaded, go to Narrator ...
Create custom voice models and synthesize speech with Microsoft's Speech Studio.
Read Aloud uses the proofing language set for the document. To change the language, see the help article Fix text-to-speech reading in wrong language. Voices. Depending on your platform, text-to-speech (TTS) uses software that comes built into your device or by a Microsoft service. The voices available will differ between TTS services.
Azure AI text to speech supports various streaming and non-streaming audio formats, with the commonly used sampling rates. All TTS prebuilt neural voices are created to support high-fidelity audio outputs with 48 kHz and 24 kHz. The audio can be resampled to support other rates as needed. See Audio outputs.
The Speech service allows you to convert text into synthesized speech and get a list of supported voices for a region by using a REST API. In this article, you learn about authorization options, query options, how to structure a request, and how to interpret a response. Tip. Use cases for the text to speech REST API are limited.
Both Google Cloud Text-to-Speech and Amazon Polly offer open-source text-to-speech engines with limited free tiers. While not entirely open-source, they give access to **cutting-edge** text-to-speech technology and AI voice options. They support customization for various use cases, from audiobooks to voice assistants. Key Advantages: