# huggingface/speech-to-speech

Build voice agents with open-source models

Repository: https://github.com/huggingface/speech-to-speech
Canonical: https://ross.abutalabs.com/products/speech-to-speech
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, assistant, language-model, machine-learning, python, speech, speech-synthesis, speech-to-text, speech-translation
Last push: 2026-08-26T12:53:03+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 84, longevity 54
- inputs: {"age_days": 756, "days_push": 7, "days_rel": 28, "gap_med": 52, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12882, forks 1595 (observed 2026-08-28T04:10:59.989394+00:00)

## What it is
A low-latency, fully modular voice-agent pipeline (VAD -> STT -> LLM -> TTS) built from open-source models, exposed via the OpenAI Realtime event set over WebSocket and WebRTC. Every component is swappable, supporting hosted providers or fully local stacks with vLLM or llama.cpp.

## Use cases
- build a voice assistant with open-source models
- run a fully local speech-to-speech pipeline
- serve an OpenAI Realtime-compatible voice agent endpoint
- swap STT, LLM, and TTS components in a voice pipeline
- add conversational voice backend to a robot
- translate speech to speech in real time

## When to choose
- you want a modular, swappable voice-agent pipeline with open-source models
- you need OpenAI Realtime API compatibility without OpenAI
- you want a fully local, self-hosted voice stack
- you need low-latency voice conversation for robots or apps

## When to avoid
- you only need simple text-based chatbots without audio
- you want a turnkey closed-source commercial voice product
- you need non-Python tooling or managed-only deployment

## Facets
- artifact type: framework
- maturity: active
- function: speech-recognition, tts, llm-inference, websocket, agent-framework, chatbot
- domain: speech-processing, artificial-intelligence, large-language-models
- platform: python, cross-platform, self-hosted
- tags: voice-agents, speech-to-speech, vad, openai-realtime-api, webrtc, low-latency, modular-pipeline, ai-agents, voice, web-server

## Member repositories
- huggingface/speech-to-speech (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:59.989394+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:13:42.712825+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/speech-to-speech (fetched 2026-08-28T04:10:59.989394+00:00, sha 0080c739ee39)
  - registry_pypi: https://pypi.org/pypi/speech-to-speech/json (fetched 2026-08-29T08:09:43.743884+00:00, sha 43023e770fc1)
- Data as of 2026-08-30T08:39:29.467469+00:00.