POST
/
v1
/
audio
/
transcriptions
curl -X POST "https://api.applerouter.ai/v1/audio/transcriptions" \
  -H "Authorization: Bearer sk-your-api-key" \
  -F "file=@audio.mp3" \
  -F "model=whisper-1" \
  -F "response_format=json"

{
  "text": "Hello, this is a test transcription of the audio file."
}

​
Overview

Transcribe audio files to text using models like Whisper.
​
file
file
required
The audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm
​
model
string
required
The model to use (e.g. whisper-1)
​
language
string
ISO-639-1 language code (e.g. en, zh, ja)
​
prompt
string
Optional text to guide the model’s style or continue a previous segment (Prompt)
​
response_format
string
Response Format: json, text, srt, verbose_json, or vtt
​
temperature
number
Sampling Temperature (0-1)
​
timestamp_granularities
array
Timestamp granularity: word, segment
curl -X POST "https://api.applerouter.ai/v1/audio/transcriptions" \
  -H "Authorization: Bearer sk-your-api-key" \
  -F "file=@audio.mp3" \
  -F "model=whisper-1" \
  -F "response_format=json"

{
  "text": "Hello, this is a test transcription of the audio file."
}

Authorizations

​
Authorization
string
header
required

使用 Bearer Token 认证。格式: Authorization: Bearer sk-xxxxxx

Body

multipart/form-data
​
file
file
required

音频文件

​
model
string
required
Example:

"whisper-1"

​
language
string

ISO-639-1 语言代码

Example:

""

​
prompt
string
Example:

""

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

"json"

​
temperature
number
Example:

0

​
timestamp_granularities
enum<string>[]
Available options:
word,
segment
Example:

""

Response

200 - application/json

成功转录

​
text
string