audiobooks

Transcribe Audiobook Audio

Transcribe audio clips using OpenAI Whisper.

Reuses the same transcribe_audio logic from stories.

Accepts audio files (.mp3, .wav, .m4a, .webm) and returns transcription. Transcription is forced to English language.

Returns: JSON payload ➜ { "text": "<transcribed text>" }

post/audiobooks/transcribe

Request

  • Base URL: https://api.pixleyai.com (the document declares no server; this is the origin it was published from)
  • URL: https://api.pixleyai.com/audiobooks/transcribe
  • Auth: HTTP bearer

Response

Successful Response

unknown required

Changes

No recorded changes to this operation across all 1 revision of this API.