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.
🔥🔥 Kokoro in Rust. https://huggingface.co/hexgrad/Kokoro-82M Insanely fast, realtime TTS with high quality you ever have.
| Date | Stars |
|---|---|
| 2026-07-24 | 799 |
| 2026-07-25 | 801 |
| 2026-07-28 | 801 |
| 2026-07-30 | 801 |
| 2026-07-31 | 806 |
| 2026-08-04 | 807 |
| 2026-08-05 | 806 |
| 2026-08-06 | 806 |
Today
— stars today
This week
+5 stars this week
This month
— stars this month
Momentum
5.0
growth rate 0.62%/day
<div align="center"> <img src="https://img2023.cnblogs.com/blog/3572323/202501/3572323-20250112184100378-907988670.jpg" alt="Banner" width="400" height="190"> </div> <br> <h1 align="center">🔥🔥🔥 Kokoro Rust</h1> ## [Zonos Rust Is On The Way?](https://github.com/lucasjinreal/Kokoros/issues/60) ## [Spark-TTS On The Way?](https://github.com/lucasjinreal/Kokoros/issues/75) ## [Orpheus-TTS On The Way?](https://github.com/lucasjinreal/Kokoros/issues/75) **ASMR** https://github.com/user-attachments/assets/1043dfd3-969f-4e10-8b56-daf8285e7420 (typo in video, ignore it) **Digital Human** https://github.com/user-attachments/assets/9f5e8fe9-d352-47a9-b4a1-418ec1769567 <p align="center"> <b>Give a star ⭐ if you like it!</b> </p> [Kokoro](https://huggingface.co/hexgrad/Kokoro-82M) is a trending top 2 TTS model on huggingface. This repo provides **insanely fast Kokoro infer in Rust**, you can now have your built TTS engine powered by Kokoro and infer fast by only a command of `koko`. `kokoros` is a `rust` crate that provides easy to use TTS ability. One can directly call `koko` in terminal to synthesize audio. `kokoros` uses a relative small model 87M params, while results in extremly good quality voices results. Languge support: - [x] English; - [x] Chinese (partly); - [x] Japanese (partly); - [x] German (partly); > 🔥🔥🔥🔥🔥🔥🔥🔥🔥 Kokoros Rust version just got a lot attention now. If you also interested in insanely fast inference, embeded build, wasm support etc, please star this repo! We are keep updating it. New Discord community: https://discord.gg/E566zfDWqD, Please join us if you interested in Rust Kokoro. ## Updates - **_`2025.07.12`_**: 🔥🔥🔥 **HTTP API streaming and parallel processing infrastructure.** OpenAI-compatible server supports streaming audio generation with `"stream": true` achieving 1-2s time-to-first-audio, work-in-progress parallel TTS processing with `--instances` flag support, improved logging system with Unix timestamps, and natural-sounding voice generation through advanced chunking; - **_`2025.01.22`_**: 🔥🔥🔥 **CLI streaming mode supported.** You can now using `--stream` to have fun with stream mode, kudos to [mroigo](https://github.com/mrorigo); - **_`2025.01.17`_**: 🔥🔥🔥 Style mixing supported! Now, listen the output AMSR effect by simply specific style: `af_sky.4+af_nicole.5`; - **_`2025.01.15`_**: OpenAI compatible server supported, openai format still under polish! - **_`2025.01.15`_**: Phonemizer supported! Now `Kokoros` can inference E2E without anyother dependencies! Kudos to [@tstm](https://github.com/tstm); - **_`2025.01.13`_**: Espeak-ng tokenizer and phonemizer supported! Kudos to [@mindreframer](https://github.com/mindreframer) ; - **_`2025.01.12`_**: Released `Kokoros`; ## Prerequisites To build this project locally, you need the following system dependencies: ### macOS ```bash brew install pkg-config opus ``` ### Linux (Ubuntu/Debian) ```bash sudo apt-get install pkg-config libopus-dev ``` ## Installation 1. Download the required model and voice data files: ```bash bash download_all.sh ``` This will download: - The Kokoro ONNX model (`checkpoints/kokoro-v1.0.onnx`) - The voices data file (`data/voices-v1.0.bin`) Alternatively, you can download them separately: ```bash bash scripts/download_models.sh bash scripts/download_voices.sh ``` 2. Build the project: ```bash cargo build --release ``` 3. (Optional) Install Python dependencies for OpenAI client examples: ```bash pip install -r scripts/requirements.txt ``` 4. (Optional) Install the binary and voice data system-wide: ```bash bash install.sh ``` This will copy the `koko` binary to `/usr/local/bin` (making it available system-wide as `koko`) and copy the voice data to `$HOME/.cache/kokoros/`. ## Build using Nix ```bash nix develop cargo build --release ``` or with CUDA support: ```bash nix develop .#cuda cargo build --features kokoros/cuda --release ``` ## Usage ### View available options ```bash ./target/release/k
Excerpt of 12,059 characters
Read on GitHub
MagicSource · Google
66
12
11
10
9
7
6
5
5
4
3
3
3
Victor Sonck
2
Alistair Keiller · UCI CS 2027
2
Stijn Tintel · Adlevio · Bulgaria
2
2
Rik Huijzer
2
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:30f9b1df3db97aee, topic:tts, readme:audio generation