Copyable requests
curl
curl -F "audio=@meeting.mp3" https://agentmediatools.com/api/transcribeSpeech to Text API
Transcribe audio with Whisper
Transcribe an audio upload or public audio URL with Whisper-compatible speech recognition. Returns text, language, timed chunks, and SRT when available. One free call daily, then 2 flexible credits.
✓ Transparent usage terms✓ REST + MCP✓ Real browser tool
Working examples
Copy it into your stack.
Upload audio up to 20 MB or provide a public URL. The response includes text and, when available, language, timed chunks, duration, and SRT.
Example JSON response
{"success":true,"text":"Welcome to the meeting.","language":"en","chunks":[],"srt":null,"duration":4.2}Download URLs are temporary. Save results to your own storage when the workflow needs durable retention.
What you can build
- ✓ Turn meetings and interviews into searchable text
- ✓ Generate subtitles from timed speech segments
- ✓ Feed transcripts into agent summaries and archives
Frequently asked questions
How is transcription billed?
The first call each day is free, then each attempt uses 2 flexible credits.
What is the upload limit?
Direct audio uploads are limited to 20 MB; use a public URL for larger source files.
Does it return subtitles?
When the upstream result includes timed chunks, the API also returns SRT text.
One tool now, one integration later
Test it in the browser. Automate it when ready.
The same Agent Media Tools account connects this operation to the wider Tool API and MCP catalog.