# Speech-To-Speech-CPU

Speech-To-Speech-CPU is a self-hosted ai app. Speech-To-Speech-CPU runs Hugging Face's open-source realtime voice-agent pipeline (Apache-2.0, 13k+ stars): voice activity detection, speech-to-text (faster-whisper), any OpenAI-compatible LLM as the brain, and Kokoro... It is open source and self-hosted, installable on Unraid.

Canonical page: https://ourlocalhost.com/app/7605/speech-to-speech-cpu

## Description

Speech-To-Speech-CPU runs Hugging Face's open-source realtime voice-agent pipeline (Apache-2.0, 13k+ stars): voice activity detection, speech-to-text (faster-whisper), any OpenAI-compatible LLM as the brain, and Kokoro text-to-speech — served as one OpenAI Realtime WebSocket server. Point any Realtime-API client at it instead of OpenAI's cloud: Conduit's "local listening" (speech server), OpenAI Agents SDK clients, LiveKit, or its own browser demo. This template runs a CPU image built and published by Aurial (upstream ships CUDA-only and no registry image), so it needs no GPU and can run alongside GPU inference servers. It has no web page of its own: it is a backend that apps connect to. Set its three LLM fields to point at an existing OpenAI-compatible server (Strata, Radiance, Ollama, LM Studio, …); the key is stored masked, never on the command line. One voice session at a time.

## Platform availability

Available on 1 of 10 platforms: Unraid.

## Health score

82/100 (Excellent), based on 4 of 5 factors.
- Maintained: 100 (last commit 10 days ago)
- Popular: 83 (13,679 GitHub stars)
- Easy to install: 35 (1 install platform, install notes, Docker image)
- Security check: 94 (no serious findings, 1 minor, CI, tests)

## Links

- Unraid: https://ca.unraid.net/apps/app_12929a9d353c2037
- GitHub: https://github.com/huggingface/speech-to-speech

## Common questions

### Do I need an OpenAI or other cloud API key to run it locally?

No. It is described as starting a conversation with one command without an API key or cloud service.

### What should I do when using speakers so the assistant does not hear itself?

Add --echo-cancellation when running on speakers. This lets you still interrupt by voice; headphones do not need it.

### Does the first run take extra time?

Yes, the first run downloads the models. Allow a few minutes before it is ready to speak.

### Can existing OpenAI Realtime clients connect to it?

Yes. The server speaks the OpenAI Realtime protocol over WebSocket and WebRTC, so Realtime API clients can point at it.

### How can I enable more verbose or diagnostic output?

Add --verbose for diagnostic output, and use --log_level debug for more detailed local logs. Raw event output is available with local --local_audio_print_json or talk --print-json.

### Is the default Linux Qwen3-TTS wheel generic across systems?

No. The default Linux wheel targets CUDA 12.8 and Ubuntu 24.04, and the README points to the CUDA note for other systems.

---
Source: Our Local Host (https://ourlocalhost.com/app/7605/speech-to-speech-cpu), the self-hosted and open-source app directory.
