Plain-AyI
← All projects
Speech & audio

SenseVoice

A speech model that writes out what was said and also detects the language, emotion and sounds like laughter.

Research-backedNew this week

What it does

SenseVoice is a speech AI model. The released version turns speech in Mandarin, Cantonese, English, Japanese and Korean into text and identifies which language is spoken.

It also tags emotions and common sounds such as music, applause, laughter, crying and coughing. Its makers say it is fast and compares well with Whisper on Chinese and Cantonese.

Developers can fine-tune it and run it as a service that other programs connect to.

Who it's for

Developers building transcription or voice features, especially for Chinese and other Asian languages.

Can I use it without coding?

Developers only. It is used through Python code, though online demos let you try it in a browser. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Linux, Server
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it