Skip to main content
POST
Speech-to-text
We accept both multipart and JSON base64 for STT, so the OpenAI SDK works out of the box.

Multipart (OpenAI SDK default)

JSON base64 (light HTTP clients)

Response formats

json (default), text, srt, verbose_json (with segments + word timestamps), vtt.

Limits

  • Max 25 MB audio per request
  • Formats: MP3, MP4, M4A, WAV, WebM, OGG, FLAC

Authorizations

Authorization
string
header
required

API key in format: Bearer inf_***

Body

application/json
model
string
required

Model ID to use for STT

audio
string
required

Base64-encoded audio data

language
string

Language of the audio (ISO-639-1)

response_format
enum<string>
default:json
Available options:
json,
text,
srt,
verbose_json,
vtt

Response

Transcription result. Shape depends on response_format: JSON (json, verbose_json) or plain text (text, srt, vtt).

response_format: json (default) or verbose_json

text
string
Example:

"Hello, this is a test transcription."

language
string

Detected language (verbose_json only)

Example:

"en"

duration
number

Audio duration in seconds (verbose_json only)

Example:

12.5

segments
object[]

Time-stamped segments (verbose_json only)

credits_used
integer
Example:

3