Skip to main content
POST
Transcribe audio to text using Whisper

Body

application/json
audioUrl
string
required

URL of the audio file to transcribe

language
string

Language code (e.g., pt, en, es). Auto-detect if not provided.

provider
enum<string>
default:openai

Transcription provider

Available options:
openai,
deepgram,
assemblyai,
google
model
string

Model to use (provider-specific)

Example:

"whisper-1"

Response

Transcription result: { text, language?, duration?, provider? }.