Skip to main content
POST
Create Transcription
POST /audio/transcriptions Upload an audio file and get a text transcript. OpenAI-compatible multipart API.

Limits

Billing is per minute of audio (minimum 1 second). Rates are listed on each model in /v1/models.

Request (multipart)

file
file
required
Audio file to transcribe
model
string
required
STT model ID (e.g. deepgram-nova-3, whisper-large-v3-turbo)
language
string
ISO-639-1 code, or auto / multi where supported
response_format
string
json (default), text, srt, verbose_json, or vtt
prompt
string
Optional hint text (Whisper-family models)
temperature
number
01 (ignored by some engines)
model_config
string
JSON string of engine options (Deepgram: smart_format, punctuate, diarize, …)
You can also pass Deepgram flags as flat form fields: smart_format, punctuate, diarize, utterance, numerals.

Response

Default (json):
text / srt / vtt return a plain-text body. verbose_json may include extra fields such as duration.

Models

Usable models (see /v1/models for live pricing):

Examples

Authorizations

Authorization
string
header
required

Enter your API key (starts with 'ek-')

Body

multipart/form-data
file
file
required

Audio file (flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm). Max 25 MB / 25 minutes.

model
string
required

STT model ID

Example:

"deepgram-nova-3"

language
string

ISO-639-1 code, or auto/multi where supported

Example:

"auto"

prompt
string

Optional hint text (Whisper-family)

response_format
enum<string>
default:json
Available options:
json,
text,
srt,
verbose_json,
vtt
temperature
number
Required range: 0 <= x <= 1
model_config
string

JSON string of engine-specific options (e.g. Deepgram)

smart_format
boolean
punctuate
boolean
diarize
boolean
utterance
boolean
numerals
boolean

Response

Transcription result

text
string
required

Transcribed text

Example:

"Hello, how are you?"

duration
number

Audio duration in seconds (verbose_json)