Skip to main content
POST
/
v1
/
audio
/
transcriptions
curl https://www.qingbo.dev/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1"

{
  "text": "欢迎使用 清波 API 语音识别服务。"
}

Documentation Index

Fetch the complete documentation index at: https://docs.qingbo.dev/llms.txt

Use this file to discover all available pages before exploring further.

Synchronous endpoint — returns the recognition result directly when the request completes. 
curl https://www.qingbo.dev/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1"

{
  "text": "欢迎使用 清波 API 语音识别服务。"
}

​
Available Models

Model IDDescription
whisper-1OpenAI Whisper, supports multilingual recognition

​
Two Endpoints

​
Speech-to-text

POST /v1/audio/transcriptions
Transcribe audio into text in its original language.

​
Speech translation

POST /v1/audio/translations
Translate audio into English text. Parameters are the same as the transcription endpoint.

​
Request Parameters

Use the multipart/form-data format:
​
file
file
required
Audio file. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm.
​
model
string
required
Model ID: whisper-1

​
Response

​
text
string
The recognized or translated text.