AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Students › SenseVoice
✦ Free & open sourceStudents

SenseVoice

Multilingual ASR, emotion recognition, and audio event detection model.

SenseVoice Speech Foundation Model

Multilingual speech recognition, emotion detection, and audio event analysis for developers.

Free forever · open source · MIT
✓ Light setup✓ Browser-based✓ Real-time collaboration
7.5
ZEKAI
Fast multilingual ASR model
Free & open source · Students
Ease of setup4
Usefulness8
Maintenance9.5
Community8.5
★ 9,400
GITHUB
Sep 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

SenseVoice is an open-source speech foundation model providing ASR, language identification, speech emotion recognition, and audio event detection. It suits developers and researchers processing Mandarin, Cantonese, English, Japanese, and Korean audio.

Runs on
Cross-platform
Hosting
Self-host
Languages
C
License
MIT

What it is

The model processes audio through a non-autoregressive end-to-end framework to deliver low-latency transcriptions alongside rich emotion and sound event tags. It supports optional FSMN-VAD segmentation for long audio or a bounded-memory windowing script for hour-scale recordings.

Who it's for

It suits engineers and researchers building voice applications or analyzing multilingual audio datasets with emotion tagging requirements. It does not suit users looking for a finished end-user transcription application without Python development work.

Key features

Multilingual ASR

Supports automatic speech recognition and language ID for Mandarin, Cantonese, English, Japanese, and Korean.

Speech Emotion Recognition

Detects emotion tags from raw audio without relying solely on formatted text transcriptions.

Audio Event Detection

Identifies common human-computer interaction events including background music, applause, laughter, crying, and coughing.

Efficient Inference

Employs a non-autoregressive end-to-end architecture to achieve low-latency inference performance.

How to start

Up and running in 3 steps

1
Install the required FunASR package via pip install -r requirements.txt.
2
Configure the AutoModel loader in Python specifying the iic/SenseVoiceSmall model path and device.
3
Run inference using model.generate with your target audio file and process output with rich_transcription_postprocess.
Real talk

Our honest verdict

What's great

  • Significantly faster inference than autoregressive alternatives like Whisper at comparable parameter counts.
  • Built-in emotion recognition and audio event tags accompany standard transcription output.
  • Includes bounded-memory windowing scripts for processing hour-scale recordings without VAD.
  • Provides service deployment pipelines supporting multi-concurrent requests across multiple languages.

Where it falls short

  • Requires technical skill in Python, FunASR, and model configuration to set up and run.
  • Running inference efficiently demands dedicated GPU hardware resources.
  • Speaker diarization requires composing separate FSMN-VAD and CAM++ models rather than native output.
Cost

Pricing & license

Free under its MIT licence, with no paid hosted options mentioned in the repository. The only cost is running it on your own hardware.

Paid work

Open remote AI-training roles

873 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives
Get more

Use it, or have us set it up

📄 Free PDF: SenseVoice for Students
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure SenseVoice for you — and train your team.
Get it done for you ↗
Questions

FAQ

Which languages does the released checkpoint support?

The released SenseVoiceSmall checkpoint supports Mandarin, Cantonese, English, Japanese, and Korean.

How does it handle long audio recordings?

You can segment audio using FSMN-VAD or use the provided long_audio_no_vad.py script which decodes via ffmpeg on fixed 30-second windows.

Does the model perform speaker diarization natively?

No, speaker diarization is handled through a composed FunASR pipeline using separate FSMN-VAD and CAM++ models.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Students — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google