Audio
Whisper Large v3
Audio transcription and subtitle generation.
whisper-large-v3Designed for your workflow
From input to useful output.
InputAudio file
ModelWhisper Large v3
OutputTranscript
Explore these use cases
- 01Meeting transcription
- 02Subtitle workflows
- 03Searchable audio archives
Model capabilities
Published catalog- Context window
- Not applicable
- Maximum output
- Transcript
- Serving region
- Thailand · TH
- Streaming
- Not listed
- Tool use
- Not listed
- Structured output
- Not listed
- Reasoning
- Not listed
Catalog specifications describe the model configuration. Check service status before sending requests.
Build with this model
Upload audio as a multipart request to the transcription endpoint. The published rate is per minute of audio.
- API base URL
https://b300.powerchampion.ai/v1- Endpoint
- POST
/v1/audio/transcriptions - Authentication
Authorization: Bearer YOUR_API_KEY