Plain-AyI
← All projects
Speech & audio

PaddleSpeech

A toolkit that turns speech into text, text into speech, and translates spoken English into Chinese.

Research-backedNew this week

What it does

PaddleSpeech is a collection of speech tools built on PaddlePaddle, a deep-learning platform from Baidu. It can write out what was said in a recording, read text aloud in natural-sounding voices, and translate English speech into Chinese text.

It also handles related jobs: adding punctuation to raw transcripts, recognising who is speaking, spotting wake words and sorting sounds into types. It is especially strong on Chinese, including mixed Chinese and English.

It can be used from the command line or run as a server, including live streaming recognition and speech. The project won a best demo award at a research conference in 2022.

Who it's for

Developers and researchers building speech features, especially for Chinese-language products.

Can I use it without coding?

Developers only. Needs Python and some technical setup; it is a toolkit rather than a ready-made app. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Linux, Windows, Mac
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 (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it