Free. Fully featured.
Polyphon
The full application, free to use.
Download it, run it, keep it — no card required.
Voices & Sessions
- Multi-voice sessions with unlimited voices
- Broadcast and conductor session modes
- API voices — Anthropic Claude, OpenAI GPT, Google Gemini, and more
- CLI voices — Claude Code, Codex, GitHub Copilot, and more
- Custom OpenAI-compatible endpoints — Ollama, LM Studio, and more
- Voices hear each other and can build on each other's responses
- Full conversation history stored locally
Compositions & Settings
- Save and reuse voice configurations with Compositions
- Custom tones and system prompt templates
- Conductor profile — name, pronouns, and context injected into every session
- Per-voice model selection and system prompts
Privacy & Data
- Local-first — your conversations never leave your machine
- No account required — just download and run
- No usage limits from Polyphon (you pay your API providers directly)
- No telemetry without explicit opt-in
Our commitment
Polyphon is built for people who want to think with multiple AI voices at once. The core experience — multi-voice sessions, all provider types, local-first storage — is free. We'll only charge for services that add genuine value on top of that foundation.
If you want to support development today, the best thing you can do is download Polyphon, share it with someone who'd find it useful, or leave a star on GitHub.
Polyphon
/ˈpɒl.i.fōn/ · POL-ee-fone
The name comes from polyphony — the musical practice of weaving multiple independent voices together into a single composition. In music, polyphony is what separates a lone melody from a full ensemble. Polyphon brings that same idea to AI: instead of a single model answering in isolation, multiple voices respond, react to each other, and build on what came before. One chat. Many voices.