# FunASR

> Speech recognition toolkit

Training and inference for streaming ASR, voice activity detection, punctuation and speaker diarization.

- Source: https://github.com/modelscope/FunASR
- License: MIT
- Language: Python
- Stars: 20570
- Forks: 2056
- Contributors: 210
- Last commit: 2026-10-02
- Latest release: v1.4.16 (2026-09-18)
- Purpose: AI & LLM tooling, Media & photos
- Runs on: Docker / self-host, Library / SDK
- For: Personal, Enterprise

## Worth score: 80/100

How much DigGitHub recommends it, from activity, adoption, docs, license and security signals.

- Popularity: 22/25
- Momentum: 10/20
- Maintenance: 25/25
- Community: 12/15
- Readiness: 11/15

## Alternatives

- [WhisperLiveKit](https://diggithub.com/QuentinFuxa/WhisperLiveKit.md): Real-time local speech-to-text
- [Fish Speech](https://diggithub.com/fishaudio/fish-speech.md): State-of-the-art open TTS
- [MoneyPrinterTurbo](https://diggithub.com/harry0703/MoneyPrinterTurbo.md): Generate short videos from a topic with AI
- [whisper.cpp](https://diggithub.com/ggml-org/whisper.cpp.md): Whisper speech recognition in C/C++
- [HyperFrames](https://diggithub.com/heygen-com/hyperframes.md): Write HTML, render video
- [VoxCPM](https://diggithub.com/OpenBMB/VoxCPM.md): Tokenizer-free multilingual TTS
- [VibeVoice](https://diggithub.com/microsoft/VibeVoice.md): Microsoft's open voice AI models
- [WhisperX](https://diggithub.com/m-bain/whisperX.md): Speech recognition with word timestamps

---

Source page: https://diggithub.com/modelscope/FunASR
Updated: 2026-10-03