跳转到主要内容
Send a POST request to https://api.qhaigc.net/v1/audio/transcriptions to convert an audio file into text. The qhai-asr-lite model is optimized for speed and accuracy across a wide range of languages. If you do not specify a language, the model detects it automatically.

​
Request

POST https://api.qhaigc.net/v1/audio/transcriptions
The request body must use multipart/form-data encoding.

​
Parameters

​
file
file
必填
The audio file to transcribe. Supported formats include mp3, wav, m4a, ogg, flac, and webm.
​
model
string
必填
The transcription model to use. Set this to "qhai-asr-lite".
​
language
string
The language of the audio as an ISO-639-1 code (for example, "zh" for Chinese or "en" for English). If omitted, the model detects the language automatically.
​
response_format
string
The format of the transcription output. Options are "json" (default), "text", "srt", and "vtt".

​
Response

​
text
string
The transcribed text content of the audio file.

​
Example response

{
  "text": "你好，这是启航 AI 的语音识别服务测试。"
}

​
Code examples

import openai

client = openai.OpenAI(
    api_key="sk-your-api-key-here",
    base_url="https://api.qhaigc.net/v1"
)

with open("audio.mp3", "rb") as audio_file:
    transcription = client.audio.transcriptions.create(
        model="qhai-asr-lite",
        file=audio_file
    )

print(transcription.text)