Skip to main content
POST
/
v1
/
audio
/
transcriptions
cURL
curl -s 'https://api.deerapi.com/v1/audio/transcriptions' \
  -H "Authorization: Bearer $DEERAPI_KEY" \
  -F 'model=whisper-1' \
  -F 'prompt=A cinematic shot of a quiet city street at sunset.' \
  -F 'response_format=json' \
  -F 'file=@/path/to/audio.mp3'

{
  "text": "Hello, welcome to DeerAPI."
}

​
Overview

Use this endpoint to call the STT workflow through DeerAPI. The API reference on this page shows the request schema, response schema, authentication requirements, and runnable examples for the configured endpoint.

​
Before you start

Use the DeerAPI base URL and pass your API Key in the Authorization header: 
https://api.deerapi.com

Authorization: Bearer $DEERAPI_KEY

​
Model selection

Choose a current model ID from the live pricing page. Model availability changes over time, so avoid copying a model ID from an old project without checking the live list first.

​
Implementation notes

  • Use the OpenAPI playground for the exact request fields accepted by this endpoint.
  • Keep API Keys on the server side when you build production applications.
  • Log the request ID from failed calls so support can investigate the request.
  • Retry 429, 500, and 503 responses with exponential backoff.

Authorizations

​
Authorization
string
header
required

Use a DeerAPI API Key as a Bearer token.

Body

multipart/form-data
​
file
file
required

The audio file to transcribe. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.

​
model
string
default:whisper-1
required

The speech-to-text model to use. Choose a current speech model from the Models page.

​
language
string

The language of the input audio in ISO-639-1 format, such as en, es, or ja. Supplying the language improves accuracy and latency.

​
prompt
string

Optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

​
response_format
enum<string>
default:json

The output format for the transcription.

Available options:
json,
text,
srt,
verbose_json,
vtt
​
temperature
number
default:0

Sampling temperature between 0 and 1. Higher values produce more random output; lower values are more focused. When set to 0, the model auto-adjusts temperature using log probability.

Required range: 0 <= x <= 1

Response

200 - application/json

The transcription result.

​
text
string
required

The transcribed text.