WildcatTTS Bot Documentation

Commands

Text-To-Speech Commands

Voices

The bot provides 472 voices across 45 languages from the MiniMax speech-2.8-turbo model. If the primary provider is unavailable, the bot falls back to speech-02-turbo. Use the voice_id in commands such as !tts voice <voice_id>.

Popular Voice IDs

Popular voices from the MiniMax speech-2.8-turbo model. To select a voice, use !tts voice <voice_id> in chat.

• Wise_Woman
• Friendly_Person
• Inspirational_girl
• Deep_Voice_Man
• Calm_Woman
• Casual_Guy
• Lively_Girl
• Patient_Man
• Young_Knight
• Determined_Man
• Lovely_Girl
• Decent_Boy
• Imposing_Manner
• Elegant_Man
• Abbess
• Sweet_Girl_2
• Exuberant_Girl
• English_FriendlyPerson
• English_CaptivatingStoryteller
• English_Wiselady
• English_Deep-VoicedGentleman
• English_ConfidentWoman
• English_Comedian
• English_Jovialman
• English_Kind-heartedGirl

Complete Voice List (from Wavespeed AI minimax/speech-02-turbo Schema — fallback provider)

This list contains all 472 available voices organized by language prefix.

Note: The bot uses MiniMax speech-2.8-turbo with automatic fallback to speech-02-turbo. The list includes 472 voices categorized by language prefix. The command !tts voices links to this section.

Language Boost

The language_boost feature improves pronunciation for specific languages and dialects. This setting helps in multilingual chats and non-English streams.

Set a personal language preference with !tts language <language_name>. Moderators can set a channel default with !tts defaultlanguage <language_name>.

Available Language Boost Options

The following values are accepted:

• auto
• Afrikaans
• Arabic
• Bulgarian
• Catalan
• Chinese
• Chinese,Yue
• Croatian
• Czech
• Danish
• Dutch
• English
• Filipino
• Finnish
• French
• German
• Greek
• Hebrew
• Hindi
• Hungarian
• Indonesian
• Italian
• Japanese
• Korean
• Malay
• Norwegian
• Nynorsk
• Persian
• Polish
• Portuguese
• Romanian
• Russian
• Slovak
• Slovenian
• Spanish
• Swedish
• Tamil
• Thai
• Turkish
• Ukrainian
• Vietnamese

The auto setting uses automatic language detection. For English chats, set English. Selecting a specific language improves pronunciation for that language.

Announcements and Chat Replies

The channel language also selects the language of the text that the bot writes. This text includes stream event announcements, emote descriptions, and chat replies to commands.

For example, a viewer subscribes to a Spanish channel. The bot then makes the announcement in Spanish.

A personal language from !tts language changes the voice for your own messages only. A personal language does not change the announcements, because the whole channel hears them. The auto setting names no language, so a channel on auto gets announcements in English.

Automatic Detection

WildcatTTS reads the language that your channel declares on Twitch. The bot then sets the channel default for you.

The bot changes this setting only for a channel that has no language of its own. Your own choice always stays. Twitch has some languages that the voice engine does not support. For these languages, the channel stays on auto.

Emote Descriptions

WildcatTTS uses Google Gemini AI to describe Twitch emotes in chat messages. Instead of reading the emote code (for example, "LUL"), TTS speaks a description such as "a person laughing." The bot caches descriptions permanently to prevent repeated AI requests.

How It Works

1. When an emote appears for the first time, AI analyzes the emote image and creates a short description.
2. The bot caches the description permanently after first generation.
3. Later uses of the emote use the cached description instantly without new AI processing.

The AI writes each description in the language of the channel. The bot keeps a separate description for each language.

Managing Descriptions

Moderators can use !tts emote to view, regenerate, or set emote descriptions. See the Emote Description Management table for details.

Pronunciation Dictionary

Chat uses many short forms that TTS speaks one letter at a time. The pronunciation dictionary changes them into full words. For example, TTS speaks ngl as "not gonna lie" and glhf as "good luck have fun". WildcatTTS includes a built-in list of about 70 common short forms. You can also add your own entries.

How It Works

• The word is not case-sensitive. An entry for lfg also matches LFG.
• An entry must match a full word. An entry for fr does not change the word "friend".
• The dictionary does not change text inside a link.
• The dictionary changes each word one time. TTS does not scan replaced text for more entries.
• Some entries work in specific languages only. For example, the dictionary changes ty to "thank you" in English. In Polish, Czech, and Slovak, ty is a common word, so the dictionary keeps it.

Your Own Entries

Moderators can add entries with the !tts pronounce command or in the Web Dashboard. Custom entries are useful for channel names, game terms, and difficult words.

• Your entry replaces a built-in entry that has the same word.
• To stop a built-in entry, use !tts pronounce off <word>. To restore it, use !tts pronounce remove <word>.
• A channel can have a maximum of 100 entries.
• A new entry of your own works in all languages. An entry that replaces a built-in entry keeps the languages of that built-in entry.

How To Stop It

The dictionary is active for all channels by default. To turn it off, disable Expand Chat Acronyms in the Web Dashboard. TTS then speaks short forms letter by letter.

Profanity Filter

The profanity filter replaces rude words with milder words before TTS speaks them. For example, TTS speaks "what the fuck" as "what the freak". The filter is off until a moderator starts it.

How To Start It

Use !tts profanity block in chat, or set the "Profanity Filter" control to on in the Web Dashboard. Use !tts profanity allow to stop the filter again, and !tts profanity status to see the state, the language, and the number of words in the list. The older on and off words still work.

What It Does

• The filter replaces a rude word with a milder word. It does not remove the message, and it does not make a bleep sound.
• The filter replaces a slur with the word "slur". This replacement keeps the meaning of the slur out of the audio.
• The filter also applies to short forms from the pronunciation dictionary. When the filter is on, TTS speaks lfg as "let's freaking go".
• A word must match fully. The filter does not change the word "class".

Languages

The filter has word lists for all 40 languages that Language Boost supports. The filter uses the list for your channel language. If a viewer selects a different language for their own messages, the filter uses both lists. The filter always includes the English list, because the pronunciation dictionary is in English.

If your Language Boost is "Automatic", the filter uses the English list. The bot cannot identify the language of each message.

The English list is the largest. The lists for other languages are smaller. Slurs are in the English list only.

Banned Words

The Banned Words feature stops WildcatTTS from speaking unwanted messages. If a chat message contains a banned word or phrase, TTS skips the message completely. The bot does not generate audio for skipped messages.

How It Works

• Matching is not case-sensitive. If you ban "badword", TTS also catches "BadWord" and "BADWORD".
• TTS matches parts of words. If you ban "spam", TTS also skips messages that contain "spammer" or "spammy".
• You can ban multi-word phrases. For example, you can ban phrases such as "follow my link" or "free followers".
• TTS ignores the username in replies. If a reply mentions a user with a banned word in their name, TTS does not skip the message.

Stream Events and Redemptions

The bot handles events and chat messages differently when a message contains a banned word:

• Chat Messages: TTS skips the full message. No voice audio plays.
• Resubscriptions: The bot announces the resubscription, but omits the attached viewer message.
• Watch Streaks: The bot announces the streak count, but omits the attached viewer message.
• Channel Point Redemptions: The bot announces the reward redemption, but omits the custom text input.
• Custom Reward Policy: If a Channel Point reward has a content policy, the bot rejects redemptions that contain banned words.

How To Manage Banned Words

You can configure banned words in the Web Dashboard. Changes take effect immediately.

1. Sign in to the Web Dashboard at tts.wildcat.chat with your Twitch account.
2. Scroll to the Banned Words / Phrases card in the Ignored Users section.
3. Type a word or phrase into the input field.
4. Click Add, or press Enter on your keyboard.
5. If you want to remove an entry, click Remove next to the word in the list.

YouTube Live Chat Integration

WildcatTTS can read YouTube Live chat messages aloud into your OBS audio feed. If you stream to Twitch and YouTube at the same time, the bot reads messages from both chats into one audio source.

How It Works

• Multi-streaming support: Messages from Twitch and YouTube play through the same OBS Browser Source without extra audio setup.
• Background polling: If you turn on the feature before you start your YouTube stream, the bot waits and connects when you go live.
• Heartbeat system: The bot sends regular heartbeat signals to keep the YouTube connection active during slow chat.
• Unified formatting: Custom YouTube emotes, URLs, and channel default voice settings apply to YouTube messages automatically.

How To Enable YouTube TTS

You can configure YouTube TTS in the Web Dashboard. Changes take effect immediately.

1. Sign in to the Web Dashboard at tts.wildcat.chat with your Twitch account.
2. Scroll to the YouTube Integration card.
3. Turn on the YouTube TTS Enabled switch.
4. Enter your YouTube handle (for example, @yourchannel).
5. If your stream is already live, OBS begins speaking your YouTube chat messages immediately.

Speech-Friendly URL Reading

Chat messages often contain long web links with parameters and tracking codes. WildcatTTS simplifies links so they sound natural when spoken.

How It Works

• By default, TTS replaces links with speech-friendly domain names. For example, TTS speaks a search link as "google dot com link".
• TTS removes protocol prefixes such as "https://" and "www." before speaking the domain name.
• TTS replaces hyphens, underscores, and dots with spaces and words so the domain sounds natural.

Read Full URLs Option

If you want TTS to speak entire URLs as typed, turn on the Read Full URLs switch in the Web Dashboard. When this switch is on, TTS speaks the full link without shortening.

Chat Commands from Other Bots

Many channels run a second bot, for example Nightbot or StreamElements. Viewers control it with commands that start with "!", such as !lurk, !so or !sr. In All Messages mode, WildcatTTS reads these commands aloud as chat.

Read Chat Commands Option

To skip these messages, switch off Read Chat Commands in the Web Dashboard, or type !tts readcommands off in chat. TTS then ignores every chat message that starts with "!".

• !tts is not affected. !tts <text> is still spoken, and the other !tts commands still work.
• The option applies only in All Messages mode. The other two modes never read these messages.
• A cheer whose message starts with "!" is still read, because the viewer paid for it.

Stream Events & Privacy Controls

WildcatTTS gives you granular control over stream event announcements and viewer privacy in the Web Dashboard.

Cheer Announcements & Cheermote Filtering

When a viewer cheers bits, TTS automatically strips cheermote names like Cheer100 or Party1 from the message. TTS only reads the viewer's custom message.

Both switches are in the Cheers card of the Web Dashboard. Announce Cheers turns the "User cheered bits" alert on or off. Read Cheer Messages turns reading the attached message on or off. Cheer messages are read in every TTS mode and are not limited by TTS Permission, because the viewer paid for them.

Reward Announcements & Queued Redeems

When a viewer redeems a channel point reward, TTS speaks an alert with the reward title and the viewer message.

Use the Announce Reward Redeems switch in the Web Dashboard to turn redemption alerts on or off.

To keep one reward silent, for example a soundboard that plays its own sound, use Rewards to Announce in the Web Dashboard. Select Choose rewards and switch off the reward. The bot announces all other rewards. Moderators can use the !tts redeems mute command in chat.

By default, the bot announces a queued reward immediately when a viewer redeems it. Switch off Announce Queued Redeems Immediately to announce a queued reward only after you accept it in Twitch.

Follower Privacy & Anonymization

To protect viewer privacy, turn on the Anonymize New Followers switch in the Web Dashboard. When active, TTS announces "Someone new just followed!" instead of speaking the viewer's username.

Watch Streaks & Pronoun Resolution

When a viewer hits a watch streak milestone, the bot announces the streak count. If the viewer attached a message, the bot checks pronouns.alejo.io to speak their pronouns (for example, "They said: ...").

Web Dashboard

The WildcatTTS Web Dashboard lets broadcasters configure all TTS settings. Sign in with your Twitch account to access the dashboard.

Available Dashboard Settings

• Engine Control: Turn TTS on or off, announce stream events, and set TTS mode and permissions.
• Viewer Preferences: Allow viewer custom voices, or force the channel default voice for all messages.
• Allow Viewer Voice Preferences: Allow viewers to choose custom voices with !myvoice, or lock TTS to the channel default voice.
• Bot Responds in Chat: Turn chat text replies on or off while keeping TTS voice audio active.
• Page Language: Select the language of the dashboard text. The selector is at the top of the page. This selector does not change the voice or the announcements.
• Anonymize New Followers: Announce new followers without speaking usernames for viewer privacy.
• Announce Cheers: Turn cheer alerts on or off while continuing to read cheer messages.
• Announce Reward Redeems: Turn channel point reward redemption alerts on or off.
• Rewards to Announce: Select the rewards that the bot announces. Switch off a reward that plays its own sound.
• Announce Queued Redeems Immediately: Announce queued channel point rewards immediately without waiting for approval.
• Read Full URLs: Read full web links or only domain names.
• Read Chat Commands: Read or skip chat messages that start with "!" in All Messages mode. !tts always works.
• Cheers: Announce cheers, read the message attached to a cheer, and set the minimum Bits a cheer needs.
• Channel Points → TTS: Create and configure a custom Channel Point reward for TTS.
• YouTube Integration: Enable YouTube Live chat TTS and set your YouTube handle or stream URL.
• Ignored Users: Manage the TTS ignore list, banned words, and pronunciation dictionary.
• Banned Words / Phrases: Block specific words or phrases so TTS skips matching messages.
• Default Voice Settings: Set channel defaults for voice, volume, emotion, pitch, speed, language, and text normalization.
• Voice Calibration: Set volume multipliers for individual voices to balance audio levels.
• OBS Browser Source Setup: Get your secure OBS browser source URL and setup instructions.
• Voice Preview: Test your voice settings before you go live.

Voice Calibration

Some voices are naturally louder or quieter than other voices. Voice Calibration lets you set volume multipliers for individual voices to balance audio levels.

• Per-Voice Volume: Select a voice and assign a volume multiplier (0.1x to 10.0x). (Caution: Values over 1.0 can be loud)
• Auto-Apply: When a viewer selects a calibrated voice, the bot applies the custom volume automatically.
• Overrides: Calibrated voice volumes override the channel default volume setting.

OBS Browser Source Setup

Step 1: Add Browser Source in OBS

1. In OBS, click the "+" icon under Sources
2. Select "Browser"
3. Name the source (for example, "WildcatTTS")
4. Configure the source:
   • URL: Paste your unique TTS URL from the dashboard
   • Width/Height: Set 300x100 (size does not affect audio)
   • ✓ Control audio via OBS (must be checked)
   • Uncheck "Shutdown source when not visible" so audio plays consistently

Step 2: Enable Audio Monitoring

1. Locate the audio mixer in OBS (bottom panel)
2. Click the gear (⚙️) next to "WildcatTTS" → "Advanced Audio Properties"
3. Set "Audio Monitoring" to:
   • Monitor and Output - You and your stream hear the audio
   • Monitor Only - Only you hear the audio (for testing)

Important: Make sure that the source is unmuted in your audio mixer and the volume is set appropriately.

Troubleshooting

• Bot not responding to commands? Make sure that the bot is a moderator in your channel. Type /mod WildcatTTS in your Twitch chat. The bot requires moderator permissions to read messages and send replies.
• Bot not speaking? Make sure that TTS is enabled with !tts on in chat. Also check the active mode with !tts mode and permissions with !tts permission.
• Bot not speaking in a specific language, or reading numbers in Chinese? Set Language Boost to your language with !tts language <language_name> (or !tts defaultlanguage <language_name> for the channel). Show the active setting with !tts defaultlanguage.
• TTS generation taking too long or failing? The bot uses 302.ai with automatic fallback to Wavespeed AI. If audio delays occur, use !tts stop to cancel stuck generation. The bot retries failed requests automatically.
• Emotion not working? The auto emotion is not supported. Use neutral, happy, sad, angry, fearful, disgusted, or surprised.
• Need help? Contact the developer through the contact form at Henry's portfolio website.