Audio Transcription

intermediateproductivityMin 32K context

Transcribes audio recordings into structured text with speaker diarization, timestamps, and formatting. Supports meeting recordings, interviews, podcasts, and lectures. Handles multiple languages and accents with automatic language detection and optional translation.

Use Cases

  • Transcribing meeting recordings with speaker identification
  • Converting podcast episodes to searchable text
  • Generating subtitles from audio tracks
  • Transcribing interviews with timestamp annotations
  • Multi-language audio translation and transcription

Example Prompt

Transcribe the following audio recording.

Requirements:
1. Identify and label different speakers (Speaker 1, Speaker 2, etc.)
2. Add timestamps every 30 seconds
3. Correct filler words (um, uh) but preserve meaning
4. Format as structured text with paragraphs per speaker turn
5. Note any unclear or inaudible segments with [inaudible]
6. Provide a brief summary of key discussion points at the end

Audio: [attach audio file]

Recommended Models

Compatible Tools

kiroany

Modalities

Input: audio, text
Output: text

Related Skills

Author

OpenModels Community

@openmodelsrun
Audio Transcription — AI Agent Skill | OpenModels