Skip to main content
POST
Transcribe a multilingual audio file

Authorizations

X-API-Key
string
header
required

API key used for authentication and usage tracking.

Body

multipart/form-data
upload_file
file
required

Audio file to transcribe. Must be non-empty. Supported formats: .aac, .aiff, .flac, .mov, .mp3, .mp4, .ogg, .opus, .wav, .webm. Maximum file size: 100 MB.

language
string

Optional. The spoken language as a short code (e.g. en, es, fr, ja). When provided, the audio is transcribed directly in that language and the same value is echoed back in the language response field. When omitted, the language is detected automatically and the detected code is returned in that field.

Example:

"es"

Response

Transcription completed successfully.

text
string
required

The complete transcribed text from the audio file. Text includes automatic capitalization and punctuation. May be an empty string if no speech was recognized.

Example:

"Hola a todos. Bienvenidos a la junta semanal."

duration_ms
integer
required

The total duration of the processed audio in milliseconds.

Required range: x >= 0
Example:

4200

language
string
required

The language the transcript is in, as a short code (e.g. en, es, fr, ja).

If the request declared a language, that value is echoed back unchanged. If it was omitted, this is the language detected automatically from the audio.

For audio containing more than one language, this reports the predominant language detected. The transcript itself still reflects each part of the audio in the language spoken there.

Example:

"es"