talky 0.1.1

Talky voice AI

Talky

Voice interface for AI. Talk to OpenClaw, Moltis, Hermes or Pi. Or use MCP to talk to Claude.

Desktop

Mobile

Quick Start

Requirements: Python 3.12 or 3.13, uv, Homebrew

brew install portaudio                # required for local audio (talky say)
uv tool install talky                 # from PyPI, or: uv tool install --editable . (from source)
talky openclaw                    # Talk to OpenClaw
talky moltis                      # Talk to Moltis  
talky hermes                      # Talk to Hermes (NousResearch)
talky pi                          # Talk to Pi
talky say "Hello world"           # Test voice output

Install via uv tool, not pip. Talky installs heavy LLM / TTS / STT dependencies on-demand via uv tool install --with. Plain pip install talky into system Python leaves the on-demand installer with nowhere to write, and it will refuse with an error.

Usage

Talk to AI

• talky openclaw - OpenClaw assistant
• talky moltis - Moltis assistant
• talky hermes - Hermes agent (NousResearch)
• talky pi - Pi coding assistant
• Opens browser at localhost:9090 for voice chat

Change Voice

• talky moltis -v kokoro-uk-george - Use different voice
• talky say "test" -v google-puck - Test specific voice

List Options

• talky ls - See all available voices and profiles

Daemon / MCP (for Claude Desktop/Claude Code)

• talky daemon - Start the talky daemon (listens on 9090, serves browser UI + MCP tools)
• Any daemon-dependent command (e.g. talky openclaw) auto-spawns the daemon if it isn't running

Documentation

• Integrations - Backend and platform integrations
• Remote Access - External network access setup
• Voice Profiles - Voice configuration options

Setup

• talky config - Create config files
• Add API keys to ~/.talky/credentials/ (one JSON file per provider)

Note: The default voice profile uses local providers (kokoro TTS + whisper STT). These require brew install portaudio and will download ML models on first use. To avoid this, set a cloud voice profile in ~/.talky/settings.yaml before running.

Example API Keys

# Deepgram (speech-to-text)
echo '{"api_key":"your-key"}' > ~/.talky/credentials/deepgram.json

# Google (text-to-speech)  
echo '{"credentials":"your-credentials"}' > ~/.talky/credentials/google.json

Debug Logging

Log levels: DEBUG, INFO, WARNING, ERROR

Default: ERROR

talky --log-level INFO

# or use environment variable
TALKY_LOG_LEVEL=DEBUG talky