Documentation

Everything you need to install, configure, and use Polyphon.

Download, install, and launch Polyphon for the first time. Get up and running with your first multi-voice session.

Understand Polyphon's core vocabulary: voices, compositions, sessions, rounds, and broadcast vs. conductor modes.

Create and manage compositions — named, reusable sets of voices for launching consistent multi-agent sessions in Polyphon.

Start a session, send messages in broadcast or conductor mode, and manage conversation history in Polyphon.

Configure API keys for Anthropic, OpenAI, and Google Gemini, or set up CLI-based voice providers like claude and codex.

Add OpenAI-compatible endpoints like Ollama, LM Studio, or vLLM as custom voice providers in Polyphon.

Configure voice providers, manage tones and system prompt templates, and set up your Conductor Profile in Polyphon.

Use built-in tone presets or create custom tones to shape how each voice communicates in Polyphon sessions.

Save and reuse system prompts across voices and compositions with system prompt templates in Polyphon.

Set your name, pronouns, and background context so every voice in every session knows who they're talking to.