Stt

Speech-to-Text (STT)

Transcribe audio files to text with speaker diarization.

Available Tools

Tool	Description
60db_stt_transcribe	Transcribe audio to text
60db_stt_logs	View transcription history
60db_stt_get	Get specific transcription details

Transcribe Audio

Convert audio to text:

{
  "audio_url": "https://example.com/meeting.mp3",
  "language": "en-US",
  "diarization": true,
  "timestamps": true
}

Response:

# Transcription Complete

**Language**: en-US
**Duration**: 5:23
**Speakers**: 2

## Transcript

**[00:00:00] Speaker 1**: Good morning, everyone.
**[00:00:05] Speaker 2**: Good morning! How are you?

Parameters

Parameter	Type	Default	Description
audio_url	string	Required	URL to audio file
language	string	auto	Language code
diarization	boolean	false	Identify speakers
punctuation	boolean	true	Add punctuation
timestamps	boolean	false	Include timestamps

Usage in Claude

You: Transcribe this meeting audio
You: Transcribe with speaker identification
You: Get timestamps for the transcription

Supported Audio Formats

• MP3, WAV, M4A, OGG, FLAC
• Recommended: 44.1kHz sample rate, 128kbps+ bitrate

Related

• TTS - Text-to-speech