FunAudioLLM/Fun-ASR
Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.
This project helps convert spoken words into accurate written text, even in noisy environments or when people speak different languages or dialects. You feed it audio recordings, and it produces a precise transcription. Anyone needing to document conversations, analyze speech, or create captions from audio, such as educators, financial analysts, or content creators, would find this tool useful.
946 stars.
Use this if you need highly accurate, real-time transcriptions of audio, especially for recordings with background noise, multiple languages/dialects, or specialized industry terminology.
Not ideal if your primary need is for speaker identification and separation, as this feature is still under development.
Stars
946
Forks
81
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/FunAudioLLM/Fun-ASR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Compare
Related tools
Uberi/speech_recognition
Speech recognition module for Python, supporting several engines and APIs, online and offline.
cmusphinx/pocketsphinx
A small speech recognizer
tensorflow/lingvo
Lingvo
modelscope/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models,...
PyThaiNLP/pythaiasr
Python Thai Automatic Speech Recognition