Skip to content
Agent Search Engine.

Record · funasrSDK / libraryCosts not checkedRecord checked Jul 3, 2026

FunASR

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

Best for

Self-hosted speech recognition with VAD, punctuation, and speaker pipelines.

Avoid if

You need one blanket licence — the toolkit is MIT but model licences vary.

About FunASR

Industrial speech recognition. Up to 340x realtime, 26x faster than Whisper. 50+ languages. Speaker diarization · Emotion detection · Streaming · One API call

Quick Start · Colab · Benchmark · Model selection · Migration guide · Use cases · Deployment matrix · Models · Agent Integration · Docs · Contribute

No local setup? Open the Colab quickstart to transcribe a public sample or upload your own audio in a browser.

Recorded project text; capability claims need separate verification.

FunASR is listed in this index written primarily in Python, with 21k stars on GitHub. Its latest recorded repository push was in November 2026; that is not an ASE editorial review date.

Install

pip install torch torchaudio
For agent buildersMake your product part of the discovery.Explore advertising