7c0af41670
- SFX emoji interleaving (inline 🎉💀🔥 etc.) - Voice switching via [mode|voice] tags - Chatterbox turbo tokens ([laugh], [cough]) passthrough - Multi-segment audio concatenation via ffmpeg - Supports all modes: chatterbox, clone, dectalk, morshu, vox
TTS Toy
A RedBot cog for text-to-speech in voice chat with multiple TTS engines, emoji sound effects, and voice cloning.
Modes
| Mode | Description | Requires |
|---|---|---|
minimax |
MiniMax cloud API, natural voices | API key |
chatterbox |
Local Chatterbox server, AI voice cloning | Chatterbox server |
dectalk |
Classic 1980s robotic voice | DECTalk server |
morshu |
Morshu from CD-i Zelda | g2p_en, numpy, pydub |
vox |
Black Mesa VOX announcer | Built-in |
Switch modes: [p]ttstoy mode <mode>
Quick Start
[p]ttstoy mode chatterbox
[p]chatterbox addvoice MyVoice (attach .wav/.mp3 or paste a URL)
[p]tts Hello world [laugh] this is cool
Commands
Use [p]ttstoy to see all available commands for the current mode.
Chatterbox Voice Management
| Command | Description |
|---|---|
[p]chatterbox addvoice <name> |
Upload a voice clip (attach file or paste URL) |
[p]chatterbox removevoice <name> |
Remove a voice and delete from server |
[p]chatterbox sharevoice <name> @User |
Share a voice with another user |
[p]chatterbox myvoices |
List your voices |
[p]chatterbox temp [0.0-1.5] |
Per-voice randomness (per voice per user) |
[p]chatterbox exag [0.25-2.0] |
Per-voice expressiveness (per voice per user) |
[p]chatterbox volume [-20-20] |
Per-voice dB loudness offset (per voice per user) |
[p]chatterbox guide |
Full feature guide |
[p]chatterbox model [turbo|original] |
Switch Chatterbox model (owner) |
[p]chatterbox url [url] |
Set Chatterbox server URL (owner) |
Append reset to temp, exag, or volume to clear the setting.
General
| Command | Description |
|---|---|
[p]tts <text> |
Speak in voice chat |
[p]ttstoy myvoice [name] |
Set or view your personal voice |
[p]ttstoy voice [name] |
Set global default voice (owner) |
[p]ttstoy mode [mode] |
Show or set TTS mode (owner) |
[p]ttstoy sfxvolume [0-100] |
Set SFX volume (owner) |
[p]sfx |
List available sound effects |
[p]ttstoy info |
DM setup instructions |
DECTalk
| Command | Description |
|---|---|
[p]ttstoy dectalkinstall |
Install built-in DECTalk server |
[p]ttstoy dectalkstart |
Start server |
[p]ttstoy dectalkstop |
Stop server |
[p]ttstoy dectalkstatus |
Check server status |
[p]ttstoy dectalkautotoggle |
Toggle auto-start |
[p]ttstoy dectalkurl [url] |
Set DECTalk API URL |
DECTalk voices are controlled in-text: [:np] Paul, [:nb] Betty, [:nh] Harry, [:nf] Frank, [:nd] Dennis, [:nk] Kit, [:nu] Ursula, [:nr] Rita, [:nw] Wendy.
VOX
| Command | Description |
|---|---|
[p]ttstoy voxpack [vox|vox2] |
Switch VOX voice pack |
[p]ttstoy voxwords |
List available words |
Emoji SFX
Include emoji in your TTS text to trigger sound effects:
[p]tts Hello 🎉 world 🔥
Use [p]sfx to see all available triggers. Add .mp3 files to sfx/<folder>/ to customize.
Requirements
- RedBot 3.5+
- Audio cog loaded
- ffmpeg
requests,g2p_en,numpy,pydub(pip)