Quantatirsk/funasr-api
Speech recognition API service powered by FunASR and Qwen-ASR, supporting 52 languages, compatible with OpenAI API and Alibaba Cloud Speech API. 基于 FunASR 与 Qwen3-ASR 的语音识别 API 服务，支持 52 种语言，兼容 OpenAI API 与阿里云语音 API。
Provides containerized local deployment with multi-model support (Qwen3-ASR and Paraformer), automatic speaker diarization via CAM++, and VAD-based audio segmentation for handling long recordings. Exposes dual API compatibility through OpenAI `/v1/audio/transcriptions` and Alibaba Cloud REST/WebSocket protocols, enabling zero-code client integration. Includes GPU batch processing, far-field noise filtering, and environment-variable configuration for flexible model selection and offline deployment scenarios.
191 stars.
Stars
191
Forks
31
Language
Python
License
—
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Quantatirsk/funasr-api"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with...
k2-fsa/sherpa
Speech-to-text server framework with next-gen Kaldi
Picovoice/cheetah
On-device streaming speech-to-text engine powered by deep learning
Picovoice/leopard
On-device speech-to-text engine powered by deep learning
zaigie/FunSpeech
开箱即用的本地私有化部署语音服务，快速搭建FunASR与CosyVoice2/3后端