STT-1 speech to text api.

Access STT-1 beta, which performs neural network analysis on audio files and transcribe speeches to text.

680k: Hours of training of the model
39M: Parameters
57: Languages

Start building with a simple API call.

import { datasea } from "datasea";

const ds = new datasea("api-key");

let result = await ds.stt1.Transcribe(
  file, //audio file
);

That's all you need to start transcribing your audio files to text.

You can also call our APIs directly if you're language of choice is not TypeScript (currently the only language supported by the DataSea utility package) by calling api.dataseaai.com , more information in the docs.