Speech to text, with subtitles
Send a recording (MP3, WAV, Ogg, M4A, WebM, video files too) and get the text with timed segments, as JSON, SRT or WebVTT subtitles, or plain text. Whisper small recognises about a hundred languages, Indian ones included; it is good on clear English and fair on Indian languages. task=translate gives English text whatever was spoken. The first five minutes are heard. Options go in the query string, or as form fields when the file is sent as multipart/form-data.
Request
- Base URL: https://api.dharun.dev
- URL: https://api.dharun.dev/v1/stt
- Auth: none declared
Query parameters
auto (default) or the language spoken: en, hi, ta, te, kn, ml, mr, bn, gu, pa, ur, as, ne, sa, sd, or, ar, fr, de, es, zh, ja. Naming it helps on short clips.
transcribe (default) writes what was said; translate writes it in English.
Default json.
Response
Success
Changes
No recorded changes to this operation across all 1 revision of this API.