assemblyai_transcribe
Transcribe audio or video files with AssemblyAI, enabling speaker diarization, summarization, sentiment analysis, and entity detection for comprehensive analysis.
Instructions
Submit an audio or video file for transcription with AssemblyAI.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | Yes | AssemblyAI API key from assemblyai.com/dashboard | |
| audio_url | Yes | Publicly accessible URL of the audio/video file | |
| language_code | No | Language code (e.g. en, es, fr, de). Omit for auto-detection. | |
| language_detection | No | Enable automatic language detection | |
| speaker_labels | No | Enable speaker diarization | |
| auto_chapters | No | Generate auto chapters | |
| summarization | No | Generate a summary (also set summary_type) | |
| summary_type | No | Summary format | |
| sentiment_analysis | No | Enable sentiment analysis per sentence | |
| entity_detection | No | Enable named entity detection | |
| punctuate | No | Add punctuation (default: true) | |
| format_text | No | Format text with capitalisation | |
| webhook_url | No | URL to POST transcript results to when complete |