voicemode - Enable voice conversations with STT and TTS
Provides voice conversations, speech transcription, speech synthesis, service management, and voice configuration for AI assistants.
Tags
Updated: 2026-10-04Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Conduct voice conversations
- Transcribe spoken responses
- Synthesize spoken messages
- Manage voice services
- Configure voice preferences
- Diagnose voice setup
Inputs
- Spoken user responses
- Text messages
- Voice preferences
- Service configuration
- OpenAI API key
Outputs
- Spoken audio
- Transcribed text
- Service status
- Service logs
- Voice configuration changes
- Service state changes
Requirements
- FFmpeg
- Python 3.11 or later
- VoiceMode CLI or MCP server
- Local voice services or OpenAI API access