Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Voice (TTS & STT)

OpenCrabs supports text-to-speech and speech-to-text for voice interactions.

Text-to-Speech (TTS)

Supported Providers

ProviderVoicesSetup
ElevenLabsRachel, Adam, Antoni, Bella, etc.API key in keys.toml
OpenAIalloy, echo, fable, onyx, nova, shimmerAPI key in keys.toml
CoquiOpen-source voicesLocal installation
GTTSGoogle Translate voicesNo key needed

Configuration

# config.toml
[voice.tts]
provider = "elevenlabs"
voice_id = "Rachel"
speed = 1.0
# keys.toml
[voice]
elevenlabs_api_key = "your-key"

Speech-to-Text (STT)

WhisperCrabs

OpenCrabs integrates with WhisperCrabs for floating voice-to-text input in the TUI. Type /whisper to launch.

Supported backends:

  • OpenAI Whisper API
  • Local whisper.cpp
  • FasterWhisper

Voice Messages

When receiving a voice message on WhatsApp or Telegram:

  1. Audio is downloaded and transcribed via STT
  2. Text response is sent first (keeps chat searchable)
  3. TTS audio response is generated and sent

Per-User Voice Preferences

# config.toml
[voice.preferences.username]
voice_id = "Adam"
speed = 1.2