Frequently Asked Questions

Here are answers to the most common questions about PotatoHotDog and its AI-powered tools for Twitch streamers.

If you're setting up voice cloned TTS, troubleshooting something, or just curious how it works, you'll likely find the answer here. If not, feel free to ask in our Discord community.

Is There a Discord Server?

Yes, we have a Discord server. Feel free to join if you'd like to share comments, concerns, or suggestions. However, please note that support on the server is available in English only.

How Much Does It Cost?

Since the service is community-powered, it is completely free to use for all Twitch streamers.

However, if you find it useful, please consider supporting the project to help keep it free for everyone.

Who Maintains PotatoHotDog?

This service is maintained by me, Special Agent Squeaky.

It started as a fun side project to create a very simple text-to-speech and other AI related service for other streamers, but it quickly grew and many people began using it on their own Twitch channels.

Thanks to all the support I've received, I've now built this dedicated site to give it a better home.

What Is Twitch TTS (Text-to-Speech for Twitch)?

Text-to-speech (TTS) is a technology that converts digital text into audio, allowing the text to be read aloud using a human-like voice.

For Twitch streams, TTS allows both the streamer and viewers to hear written messages while focusing on other tasks. This makes it easier for streamers to keep up with chat and interact with their audience without needing to constantly read messages on screen.

What Is the Difference Between Concatenative and Neural Text-to-Speech (TTS)?

Text-to-speech (TTS) can be implemented in several different ways using various technological approaches. Concatenative and neural TTS are just two of these methods.

The concatenative approach is one of the most commonly used technologies. It works by concatenating (joining) pre-recorded audio snippets to synthesize a full sentence. Because this method is fast and relatively simple, the output can sometimes sound more robotic.

The neural approach uses deep learning technologies to convert phonemes (the smallest units of sound in a language) into a sequence of spectrograms, which are then turned into speech. This approach is more complex and computationally demanding, but it generally produces more natural and realistic-sounding audio.

How Do I Enable and Disable a Text-to-Speech Twitch Channel Point Reward Using an Elgato Stream Deck?

Since a text-to-speech Twitch channel point reward is typically added to OBS Studio as a browser source, you can control it by creating global hotkeys in OBS to mute and unmute the source.

Once those hotkeys are set up, simply bind them to buttons on your Elgato Stream Deck. This allows you to quickly enable or disable the text-to-speech audio during your stream with a single press.

What Is the Best Text-to-Speech (TTS) for Twitch?

Well, PotatoHotDog, of course! It's a convenient and affordable way to add a text-to-speech (TTS) channel point reward to your Twitch stream.

What Is a Text-to-Speech (TTS) Copypasta Message?

A text-to-speech (TTS) copypasta message is a funny or clever message designed to manipulate how a TTS system reads the text. These messages are often written to produce strange sounds, humorous pronunciations, or unexpected results when spoken aloud.

They are commonly used by viewers to playfully troll the Twitch streamer and entertain the rest of the chat during a stream.

Do You Need a Bot to Enable Text-to-Speech (TTS) for a Twitch Channel Point Reward?

No. A bot typically refers to a chatbot that you invite to your Twitch channel chat to read and write messages.

To listen for Twitch channel point redemptions, you don't need a chatbot. Instead, you can use a web page that listens for the redemptions and add it to OBS Studio as a browser source.

Who Is the Twitch Text-to-Speech (TTS) Voice?

One of the most well-known text-to-speech (TTS) voices is Brian, a synthesized British English male voice.

However, PotatoHotDog's TTS offers a wide variety of voices across many languages, including both male and female options, as well as AI voice cloning. This allows you to choose the voice that best fits your stream.

How Do I Let My Twitch Viewers Select the Text-to-Speech (TTS) Voice?

If you want to allow your Twitch viewers to choose which text-to-speech (TTS) voice is used, you can create a separate Twitch channel point reward for each voice and connect a TTS browser source to each reward.

This allows your community to redeem the voice they want and have their messages played using that specific TTS voice during your stream.

How Do I Ban or Block Words From Being Used in Twitch Text-to-Speech (TTS)?

Since this text-to-speech (TTS) service uses Twitch's channel point system, all you need to do is add the words you want to ban in Twitch's moderation settings.

Feel free to follow the step-by-step guide below for instructions on how to do this.

How to Instantly Mute a Twitch Text-to-Speech (TTS) Message?

This can easily be done by controlling the audio of the browser source in OBS Studio or Streamlabs Desktop. By doing so, you can quickly toggle the audio using global hotkeys or even from an Elgato Stream Deck.

Feel free to read the quick guide below for step-by-step instructions on how to set this up.

Do You Need StreamElements to Enable Text-to-Speech on Twitch Channel Point Rewards?

No. StreamElements is a live streaming platform that allows you to create web-based overlays and other tools using its APIs.

However, to listen for Twitch channel point redemptions, you can use Twitch's APIs directly - without going through StreamElements. This can easily be added as a browser source directly in OBS Studio.

What Text-to-Speech (TTS) Languages Are Supported?

A wide range of languages are supported, including English (American, British, and Australian), Spanish, Portuguese, German, French, Italian, Japanese, Korean, Norwegian, Polish, Danish, Dutch, Swedish, Turkish, Romanian, Russian, Finnish, Welsh, Icelandic, Hindi, and Arabic.

In total, the text-to-speech (TTS) system offers more than 100 voices across over 30 languages, including both male and female voices, as well as AI voice cloning. This allows you to choose the voice that best fits your stream.