text to speech bot discord

SeaVoice STT & TTS Bot

Transcribe audio channels with speech to text, synthesize messages with text to speech, and download your audio & transcription files.

Open our docs in a new tab –>

Visit our website:

SeaVoice Discord Bot Homepage –>

STT Homepage –>

TTS Homepage –>

🐙 The SeaVoice Bot is a new speech-to-text and text-to-speech Discord integration brought to you by Seasalt.ai, a startup run by some of the world’s leading experts in deep speech recognition, neural speech synthesis, and natural language processing. 🐙

Watch the demo video: https://www.youtube.com/embed/drOVk_bexFY

SeaVoice is a voice intelligence bot that uses advanced AI technology to improve the Discord voice channel experience. One of the great things about Discord’s text channels is that they maintain a permanent log of the server’s conversations. But what about the voice channels? Once something is said verbally in the channel, it’s gone - you can’t catch up on part of the conversation you missed or search the conversation later.

Invite SeaVoice to the voice channel, and you can get real time speech transcriptions delivered to a chat channel as the conversation is happening. You’ll also receive a final version of your transcript and voice recording in a DM after the session ends. SeaVoice is set apart from bots offering similar services because it’s backed by state-of-the-art deep learning models crafted by Seasalt.ai.

We feel that providing highly accurate transcriptions for voice channels is a huge accessibility improvement for Discord. Additionally, because transcriptions are automatically posted to a text channel, that means they are permanent, searchable, and shareable. Similarly, speech synthesis also boosts participation in voice channels by making them more accessible to people who can’t or don’t want to speak personally.

Capabilities

✍️ speech-to-text, transcribe audio from discord voice channels, /recognize [language].

/recognize [language] -> Bot joins the voice channel you’re currently in, and continues to listen and output transcription in real time to the chat channel. The bot will record and transcribe everyone in the voice channel. Transcriptions are output to the text channel where the initial slash command was entered. When the session ends, the bot will DM the session creator a final transcription file, an SRT-formatted transcript file (used for subtitles), and a link to a full audio download. The session will automatically wrap up if all the users leave the voice channel, or if the bot shuts down or restarts for any reason (such as when a new version gets released).

Language Support

SeaVoice currently supports 12 languages. The English and Taiwanese Mandarin models are our own in-house models trained from scratch; they are highly accurate and reliable. All other languages are supported using a multilingual open source model as the base. The performance wasn’t great out of the box, so we integrated it into our own STT pipeline and tuned the model to improve the performance. One thing you may notice with the open source model is “hallucination”. This can manifest in a couple different ways, such as: inserting words/phrases that weren’t said, transcribing in the wrong language, and/or translating the spoken language to a different language.

🗣 Text-to-Speech

Synthesize speech from chat to voice channel.

Seasalt.ai also excels at speech synthesis. We offer a text-to-speech command, which allows users to type in a chat channel and have audio synthesized and played in a particular voice channel for them.

/speak [voice] [text]

To use this command, you should already be in a voice channel. In any text channel, type the /speak slash command and then optionally specify which voice you would like to use, and enter the text that you would like synthesized. When the TTS is done speaking, a 🏁 reaction will be applied to the command message. The default voice if not specified is Orca , you can also set your own default voice using the /user_config command. You can see the available voices below:

🎙️ Record & Download

Export audio & transcriptions from voice channels.

Users are able to download their transcriptions and full audio recordings to a file.

When the STT session ends the bot will a final transcription file, an SRT-formatted transcript file (used for subtitles), and a link to a full audio download. To download the audio, follow the link and then right click in the web browser and select “Save as…”. Download links will expire after 24 hours - so if you want to a permanent copy of your file, download it to your computer.

Configuration

SeaVoice offers customizable settings for both servers and individual users.

Note: If you update any settings, you must stop and re-start any active /recognize sessions before the new configurations are applied.

👥 Server Settings

Configure settings for everyone in the server, /server_config [live_transcript] [transcript_recipients] [transcript_style] [ignore_bots] [censor].

Use the /server_config command to configure the settings for the current server that you are in. Only users with admin permissions in the server may use this command . Servers currently have the following settings:

👤 User Settings

Configure settings for just yourself, /user_config [exclude_stt] [default_tts_voice].

Use the /user_config command to configure your personal settings for your Discord account. These settings will persist no matter which server you are in. Users currently have the following settings:

⚙️ Server / User Status

Check your current server or user configurations, /server_status.

Run the /server_status command to get a break down of your current server configurations.

/user_status

Run the /user_status command to get a break down of your current user configurations.

The SeaVoice Discord bot is completely free . No sign up required. Try it out and have fun!

About Seasalt.ai

Seasalt.ai is a Seattle-based startup founded by experts in speech and language technologies.

We collect anonymized voice data for the sole purpose of improving our speech and NLP models. We will never share or sell your data. You can read our full privacy policy here .

Text-to-speech | TTS | Text to Speech | Text to Voice | Speech Synthesis Speech-to-text | STT | Transcription | Speech Recognition Real-time Artificial Intelligence | AI Communication Utility Voice Channel | Voice Chat Accessibility

AI Voice Generator

Guide on how to use text-to-speech on discord.

Looking to add a bit of personality to your Discord text channels? Discord’s Text-to-Speech (TTS) feature lets you turn written messages into spoken words, making your conversations more dynamic and engaging. Whether aiming to emphasize key points, share a laugh, or improve accessibility, TTS offers a creative way to elevate your server’s interaction.

In this guide, you’ll learn how to enable and use TTS on Discord across different platforms, as well as tips for making the most of this feature. From the step-by-step setup to managing TTS settings in your servers, this article will cover everything you need to know to get started. Let’s dive in!

Setting Up Text-to-Speech (TTS) on Discord

Text-to-Speech (TTS) on Discord can be enabled in both personal user settings and server-wide settings, giving you control over how this feature works in different contexts. You can activate TTS for your personal use, allowing you to hear messages read aloud or configure it within specific servers for broader use. 

The steps below outline how to enable TTS in your user settings and for Discord server administrators, ensuring that you and your community can take full advantage of this handy feature.

User Settings: Enabling TTS for Personal Use

• Open Discord and log in to your account.
• Click on the gear icon next to your username to open User Settings .
• Scroll down to the Accessibility section in the left-hand menu.
• Under toggle, the option Allow playback and usage of the /tts command to enable it.
• Select For all channels if you want TTS messages to play for every message that uses the /tts command . To restrict it to your server, choose For current server only.
• Exit the settings – TTS is now enabled for your account.

Server Settings: Enabling TTS for a Discord Server

• Select the server where you want to enable TTS.
• Click the server name at the top of the channel list and select Server Settings from the dropdown menu.
• In the left-hand menu, click on Text & Images .
• Scroll down to the Text-to-Speech section.
• Toggle the Allow playback and usage of /tts command option.
• Click Save Changes to apply the new settings.

With TTS successfully enabled, you can now bring your messages to life while chatting.

Using Text-to-Speech While Chatting on Discord

• Join the voice channel where you want your message to be heard.
• In the text box, type /tts followed by the message you want to send.
• Press Enter to send the message.
• Discord’s TTS engine will read the message aloud to everyone in the voice channel.

Now that you know how to use TTS in your chats, let’s explore how to customize your TTS settings for an even better experience.

Also, read their Article on Voice Changer for Discord .

Customizing Text-to-Speech Settings

• Open Server Settings for the specific server you want to customize TTS. 
• Navigate to the Text & Images tab in the settings menu.
• Toggle Allow playback and usage of /tts command to enable or disable TTS.
• Set the option to allow TTS messages to control who can send TTS messages (everyone, moderators, or specific roles).
• Adjust the TTS Output Volume to set the loudness of the TTS voice.
• Choose a TTS Voice from the dropdown menu to select the preferred voice style.
• Once satisfied with your customizations, click Save Changes to apply them.

Once you’ve customized your TTS settings, managing how and when you receive TTS notifications is essential.

Configuring Text-to-Speech Notifications

• To access User Settings, click on the gear icon next to your username in the lower-left corner.
• Under the App Settings section, select Notifications.
• For All Channels: Read all TTS notifications for every channel.
• For the Currently Selected Channel: Only read notifications for the channel you’re currently viewing.
• Never: Disable all TTS voice notifications.

With notifications set up, let’s explore how to use TTS in different languages to cater to a diverse audience.

Using TTS in Different Languages

• Open Server Settings for the server where you want to change the TTS language.
• Go to the Text & Images tab in the settings menu.
• From the TTS Voice dropdown menu, select your preferred language.
• Click Save Changes to apply the new language settings.
• Now, use the /tts command followed by text in the selected language (e.g., /tts Hola, mi nombre es Juan ).

Now that you can use TTS in various languages, here are some tips to enhance your overall TTS experience.

Tips for Using Text-to-Speech

• Moderation is key: Use the /tts command thoughtfully to avoid overwhelming others in the chat. Too many TTS messages can quickly become disruptive.
• Tailor TTS to your needs: Adjust settings like volume, voice style, and who can use TTS to ensure it fits the tone and needs of your server, creating a better experience for everyone.
• Consider others: Always be mindful of TTS’s impact on other users. Keep it fun and respectful to maintain a positive and enjoyable environment.

Finally, if you’re looking for even more advanced features, consider using third-party TTS tools to enrich your Discord experience.

Using Third-Party TTS Tools

Integrating third-party TTS tools with Discord allows you to enhance your server’s audio experience with advanced features. These tools offer better customization, more natural-sounding voices, and the ability to support various languages. Below are some options.

Resemble AI

Resemble AI is a highly versatile TTS platform known for its high-quality, lifelike voices. It excels in creating custom voices using machine learning and offers flexible integration options for Discord. Resemble AI allows users to develop unique voice clones, making it ideal for personalization in online communities. 

Features of Resemble AI:

• Custom voice creation using real-time voice cloning.
• Multiple language support for global use.
• High-quality, natural-sounding voices.
• API integration for seamless use with Discord.
• Advanced voice emotion control for more dynamic TTS.

Try Resemble AI today and take your Discord conversations to the next level!

TTS Bot is a simple, user-friendly bot specifically designed for TTS in Discord. It supports multiple languages and offers basic voice customization.

Key Features:

• Easy bot integration directly into Discord.
• Simple voice customization options.

Speechify is known for its accessible interface. It is a TTS tool that helps convert text into audio across various platforms, including Discord, with multiple voice options.

• Natural-sounding voices.
• Multi-platform support, including Discord.
• Voice speed adjustments for better clarity.

Google Cloud Text-to-Speech 

Google Cloud Text-to-Speech offers a vast library of voices with high-quality output and deep customization through Google’s cloud services.

• 220+ voices in over 40 languages.
• Custom voice tuning and intonation control.
• High-quality neural network voices.

Amazon Polly

A flexible TTS service that allows users to create applications that talk and enable speech-driven interactions.

• Wide selection of voices and languages.
• Real-time streaming for instant feedback.
• Integration with various platforms via API.

The guide has provided a comprehensive overview of effectively utilizing Discord’s Text-to-Speech (TTS) feature, from initial setup to advanced customization options. TTS enhances engagement and communication within communities, allowing users to convey their messages in a more dynamic and accessible way. By incorporating third-party tools like Resemble AI , you can take advantage of lifelike voices and personalized features that further enrich the user experience.

Explore Resemble AI today to bring more lifelike and engaging voices to your Discord conversations!

More Related to This

Introducing state-of-the-art in multimodal deepfake detection.

Oct 30, 2024

Today, we present our research on Multimodal Deepfake Detection, expanding our industry-leading deepfake detection platform to support image and video analysis. Our approach builds on our established audio detection system to deliver comprehensive protection across...

Top AI Voice Cloning Tools in 2024

Nov 6, 2024

Ever wondered what it would be like if your digital devices could speak in voices as unique as your own? Enter the realm of AI voice cloning tools, where the magic of technology allows us to create lifelike voices that resonate with personality and emotion. These...

Introducing ‘Edit’ by Resemble AI: Say No More Beeps

Aug 29, 2024

In audio production, mistakes are inevitable. You’ve wrapped up a recording session, but then you notice a mispronounced word, an awkward pause, or a phrase that just doesn’t flow right. The frustration kicks in—do you re-record the whole segment, or do you spend...

How-To Geek

How to use text-to-speech on discord.

Your changes have been saved

Email is sent

Email has already been sent

You’ve reached your account maximum for followed topics.

Quick Links

Enabling text-to-speech on a discord server, using text-to-speech on discord, muting all text-to-speech messages on discord.

While Discord is a great platform for voice communication, you might not be able to (or want to) speak with your own voice. To get around the problem, you can use Discord's built-in text-to-speech (TTS) feature.

You can use text-to-speech on your own Discord server , or on another server with a text-to-speech enabled channel. These steps only work for Discord users on Windows or Mac, as Discord's text-to-speech capabilities are unavailable to Android, iPhone, or iPad users.

Related: How to Set Up Your Own Discord Chat Server

If you want to use text-to-speech on Discord, it'll first need to be enabled in a channel on your server. If you're the server owner or administrator, you can do this in your channel settings.

To change your channel settings, access your server in the Discord desktop app or on the Discord website . From the channel listings, hover over a channel name and then click the "Settings" gear icon next to it.

In the "Settings" menu for your channel, select the "Permissions" tab on the left-hand side.

If you have roles for individual groups of users, select the role from the "Roles/Members" list, otherwise select the "@everyone" option.

A list of available permissions will be shown on the right. Make sure to enable the "Send TTS Messages" option by clicking the green check icon to the right of it.

At the bottom, select "Save Changes" to save the updated role setting.

Once enabled, users with that role (or every user, if you selected the "@everyone" role) will be able to send text-to-speech messages in the channel you modified.

You'll need to repeat these steps if you wish to enable text-to-speech in other channels.

If you're in a channel on Discord with text-to-speech messages enabled, you can send a TTS message by typing

in the chat, followed by your message.

For instance, typing

will activate your browser or device's text-to-speech capabilities, repeating the word "hello" along with the nickname of the Discord user who sent the message.

The message will also be repeated in the channel as a text message for all users to view.

If you aren't a server owner or administrator, or you just want to mute all text-to-speech messages, you can do so from the Discord user settings menu.

To access this, click the "Settings" gear icon next to your username in the bottom-left corner of the Discord app or website.

In your "User Settings" menu, select the "Text & Images" option on the left. Under the "Text-To-Speech" category on the right, click the slider to disable the "Allow playback and usage of /tts command" option.

Disabling this setting will disable text-to-speech for you on Discord, regardless of each individual server or channel setting. You'll be able to read the text element of a text-to-speech message as normal in the channel, but you won't be able to hear it repeated to you.

You'll also be prevented from using the

command yourself. You'll need to repeat these steps and reenable the option in your user settings if you wish to use it yourself later.

• Video Games