With the Whisper_Cloudflare project, this can be done in just three steps:
- One-Click Deployment: Paste the supplied worker.js code into the Cloudflare Workers platform, bind the @cf/openai/whisper-large-v3-turbo model
- API call: Get text (in JSON format) via the /raw interface, or generate subtitle files directly via the /srt interface.
- web operation: access to the Worker root path to upload audio, support for real-time preview and download of SRT files
The program handles 10,000 neuronal calculations per day for free, and 41-minute audio takes only 1.9 minutes to complete transcription.
This answer comes from the articleWhisper on Cloudflare AI: a free tool to convert audio to text and generate subtitlesThe
May not be reproduced without permission:AI productivity tools " How to realize audio to text and generate subtitles efficiently?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil