Audio
Transcribe Audio
Transcribe audio files to text. Compatible with the OpenAI Whisper API.
Supported audio formats: mp3, mp4, mpeg, mpga, m4a, wav, webm
See /audio/models for current transcription models, capabilities, and prices. Optional controls and response formats depend on the model. Unsupported combinations return 400.
post/v1/audio/transcriptions
Request
- Base URL: https://gen.pollinations.ai
- URL: https://gen.pollinations.ai/v1/audio/transcriptions
- Auth: HTTP bearer
Response
Success - Returns transcription
Changes
No recorded changes to this operation across all 1 revision of this API.