Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Build voice agents with open-source models
| Date | Stars |
|---|---|
| 2026-08-05 | 11159 |
| 2026-08-06 | 11302 |
| 2026-08-07 | 11423 |
| 2026-08-08 | 11621 |
| 2026-08-09 | 11705 |
| 2026-08-10 | 11882 |
| 2026-08-11 | 12017 |
| 2026-08-12 | 12248 |
| 2026-08-13 | 12421 |
| 2026-08-14 | 12484 |
| 2026-08-15 | 12520 |
| 2026-08-16 | 12551 |
| 2026-08-17 | 12559 |
| 2026-08-18 | 12598 |
| 2026-08-19 | 12640 |
| 2026-08-20 | 12686 |
| 2026-08-21 | 12730 |
| 2026-08-22 | 12775 |
| 2026-08-23 | 12796 |
| 2026-08-24 | 12825 |
| 2026-08-25 | 12851 |
| 2026-08-26 | 12876 |
| 2026-08-27 | 12893 |
| 2026-08-28 | 12915 |
| 2026-08-29 | 12923 |
| 2026-08-30 | 12947 |
| 2026-08-31 | 12973 |
| 2026-09-01 | 12991 |
| 2026-09-02 | 13007 |
| 2026-09-03 | 13020 |
| 2026-09-04 | 13035 |
| 2026-09-05 | 13046 |
| 2026-09-06 | 13061 |
| 2026-09-07 | 13073 |
| 2026-09-08 | 13094 |
| 2026-09-09 | 13111 |
| 2026-09-10 | 13137 |
| 2026-09-11 | 13164 |
| 2026-09-12 | 13170 |
| 2026-09-13 | 13178 |
| 2026-09-14 | 13190 |
| 2026-09-15 | 13195 |
| 2026-09-16 | 13240 |
| 2026-09-17 | 13254 |
| 2026-09-18 | 13265 |
| 2026-09-19 | 13274 |
| 2026-09-20 | 13282 |
| 2026-09-21 | 13289 |
| 2026-09-22 | 13297 |
| 2026-09-23 | 13305 |
| 2026-09-24 | 13319 |
| 2026-09-25 | 13322 |
| 2026-09-26 | 13327 |
| 2026-09-27 | 13333 |
| 2026-09-28 | 13343 |
| 2026-09-29 | 13348 |
| 2026-09-30 | 13357 |
| 2026-10-01 | 13358 |
| 2026-10-02 | 13363 |
| 2026-10-03 | 13362 |
| 2026-10-04 | 13367 |
| 2026-10-05 | 13373 |
| 2026-10-06 | 13376 |
| 2026-10-07 | 13385 |
| 2026-10-08 | 13394 |
| 2026-10-09 | 13403 |
| 2026-10-10 | 13413 |
| 2026-10-11 | 13419 |
| 2026-10-12 | 13431 |
| 2026-10-13 | 13440 |
| 2026-10-14 | 13452 |
| 2026-10-15 | 13467 |
| 2026-10-16 | 13480 |
| 2026-10-17 | 13489 |
| 2026-10-18 | 13495 |
| 2026-10-19 | 13507 |
| 2026-10-20 | 13523 |
| 2026-10-21 | 13510 |
| 2026-10-22 | 13528 |
| 2026-10-23 | 13541 |
| 2026-10-24 | 13544 |
| 2026-10-25 | 13552 |
| 2026-10-26 | 13562 |
| 2026-10-27 | 13578 |
| 2026-10-28 | 13585 |
| 2026-10-29 | 13598 |
| 2026-10-30 | 13601 |
| 2026-10-31 | 13607 |
| 2026-11-01 | 13613 |
| 2026-11-02 | 13624 |
| 2026-11-03 | 13628 |
| 2026-11-04 | 13638 |
Today
+10 stars today
This week
+53 stars this week
This month
+265 stars this month
Momentum
128.0
growth rate 0.39%/day
<div align="center">
<div> </div>
<img src="https://raw.githubusercontent.com/huggingface/speech-to-speech/main/logo.png" width="600"/>
# Speech To Speech: Build voice agents with open-source models
<p>
<a href="https://trendshift.io/repositories/20645"><img src="https://img.shields.io/badge/GitHub%20Trending-%231%20Repository%20of%20the%20Day-7B2CBF?logo=github&logoColor=white&style=for-the-badge" alt="GitHub Trending: #1 Repository of the Day"></a>
</p>
[](https://pypi.org/project/speech-to-speech/)
[](https://pypi.org/project/speech-to-speech/)
[](./LICENSE)
</div>
A low-latency voice agent built from open models that **runs entirely on your computer**. One command starts a conversation: no API key, no cloud service.
The default pipeline is **Silero VAD → Parakeet TDT → Qwen3.5-4B → Qwen3-TTS**, and every stage is swappable. The server speaks the **OpenAI Realtime protocol** over WebSocket and WebRTC, so apps built for OpenAI's Realtime API can point at your own machine instead.
This pipeline runs in production as the conversation backend for thousands of [Reachy Mini](https://huggingface.co/blog/reachy-mini) robots.
<p align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="./docs/assets/endpoint-swap-dark.gif">
<source media="(prefers-color-scheme: light)" srcset="./docs/assets/endpoint-swap-light.gif">
<img src="./docs/assets/endpoint-swap-light.gif" alt="Switching an OpenAI Realtime client endpoint from hosted OpenAI to a self-hosted speech-to-speech server" width="640">
</picture>
</p>
## Quickstart
Use CPython 3.11–3.14 (3.11 recommended):
```bash
python3 -m venv .venv
source .venv/bin/activate
pip install speech-to-speech
speech-to-speech local
```
Then talk: speak, pause, and the assistant answers through your speakers. Stop with `Ctrl+C`. The first run downloads the models, so give it a few minutes. Use headphones so the assistant does not hear itself, or add `--local_audio_block_mic_during_playback`.
By default, `local` and `talk` show final user transcripts and streaming assistant
replies once, hiding backend transcript copies, routine logs, tool details, and protocol
events. User messages are yellow and assistant replies are green in a color-capable
terminal. Startup shows `Loading models…`, followed by `Ready — start speaking.` once
the audio devices are running and the session is configured. Routine model-loading
output is hidden; startup failures show their diagnostics. Runtime warnings and errors
remain visible.
For diagnostic output, add `--verbose`:
```bash
speech-to-speech local --verbose
```
Use `--verbose --log_level debug` for more detailed local logs. Raw event output
(`local --local_audio_print_json` or `talk --print-json`) also enables diagnostic output.
On Ubuntu, first install the audio libraries with `sudo apt-get install libportaudio2 libsndfile1`. The default Linux Qwen3-TTS wheel targets CUDA 12.8 and Ubuntu 24.04; see the [CUDA note](#cuda-note-for-qwen3-tts) for other systems. On Windows, activate the environment with `.venv\Scripts\Activate.ps1`.
The default installation has the following CI coverage:
| Platform | Supported CPython versions | Checks |
|---|---|---|
| Linux | 3.11, 3.12, 3.13, 3.14 | Full test suite and installed package smoke test |
| Apple Silicon macOS | 3.11, 3.12, 3.13, 3.14 | Installed package smoke test |
Optional model backends can have narrower Python requirements. Windows is not
covered by this compatibility matrix. Python 3.10 is no longer supported following
its end of life on October 1, 2026.
Kokoro is optional on every platform. On macOS, its Misaki dependency requires
Python <3.13, so use Python 3.11 or 3.12 with `speech-to-speech[kokoro]`.
The default Qwen3-TTS backend does not require Misaki. PythExcerpt of 55,073 characters
Read on GitHub
Andrés Marafioti · Hugging Face · Switzerland
478
Hugging Face · France
53
32
wuhongsheng
13
Yoach Lacombe
8
Rohan Sharma
6
6
4
3
3
2
2
Rahim Nathwani · United States
2
2
1
Arslan Mehmood
1
1
Alex
1
Hotragn Pettugani
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8ace6c0df8ace622, topic:speech-synthesis, topic:speech-to-text, readme:speech-to-text