GPT4Audio
Transcribe & Translate audio/video files with OpeAI API.
Start new thread
Leon Havin

GPT4Audio - Transcribe & Translate audio/video files with OpeAI API.

by
Word Express - GPT-Based Word Add-In
•
GPT4Audio transcribes and translates audio/video files, including MP3, MP4, MPEG, WAV, etc. Whisper service automatically detects the language of your file and accurately generates a text on the screen. Text can be saved as: DOCX, PDF, TXT, HTML, etc.

Add a comment

Replies

Best
Leon Havin
Maker
📌
This is the first version of the product. I am going to add to it gradually, including Text-To-Speech, and better Dictation than the open source Vosk that is being used now. My Roadmap, includes the following workflow: STT => GPT => TTS, so eventually you will be able to speak to ChatGPT or other underlying models, and get vocal response.