Whisper
Package: openai-whisper · 4 nodes · Speech-to-text
Transcribe audio files using OpenAI's Whisper model. Extract text, language detection, and timestamps.
Node Reference
| Node | Type | Inputs | Outputs |
|---|---|---|---|
| Transcribe | statement | Audio Path (str), Model (whisper.Model) | Text (str), Result (whisper.Transcript), Segments (list |
| Load Model | statement | - | Model (whisper.Model) |
| Get Language | expression | Result (whisper.Transcript) | Language (str) |
| Get Timestamps | expression | Result (whisper.Transcript) | Timestamps (list |
Typical Pipeline
Load Model → Transcribe → Get Language / Get Timestamps. Text output is available directly from Transcribe.