speech-to-speech

GitHub describes it as Build local voice agents with open-source models. The repository metadata lists Python as its primary language. The metadata lists the Apache-2.0 license. This article stays within the project description and details documented in the GitHub repository README.

GitHub describes it as Build local voice agents with open-source models. The repository metadata lists Python as its primary language. The metadata lists the Apache-2.0 license. The README describes the project this way: A low-latency, fully modular voice-agent pipeline: VAD - STT - LLM - TTS , exposed through an OpenAI Realtime-compatible WebSocket API . Every component is swappable. The LLM slot speaks OpenAI-compatible protocols, so you can point it at a hosted provider, at HF Inference Providers, or at a vLLM or llama.cpp server on your own hardware for a fully local, fully open stack.

The README section "Speech To Speech: Build voice agents with open-source models" states: This pipeline runs in production as the conversation backend for thousands of Reachy Mini robots.

The README section "Quickstart" states: This starts an OpenAI Realtime-compatible server at ws://localhost:8765/v1/realtime using Parakeet TDT for local STT, an OpenAI-compatible LLM, and Qwen3-TTS for local speech output.

The README section "Quickstart" states: Any OpenAI Realtime-compatible client can connect. See Realtime API for the protocol and LLM backends for provider and local-server options.

The repository README is the source for this review. It does not replace a local installation or an independent test.

• Source 1 · Project repository
• Source 2 · README