Create transcription

Use this interface to transcribe audio into text. The interface format is compatible with the OpenAI audio/transcriptions protocol.

Request Address

Authorization

Authorization

• Type: HTTP Bearer Auth, value type string
• Required
• Description: Used to verify account information. Go to API Console , click Create Token to obtain.

Authorization: Bearer <YOUR_API_KEY>

Request Headers

Content-Type

• Type: enum<string>
• Required, fixed value multipart/form-data
• Description: The media type of the request body. Must be multipart/form-data because the audio file is uploaded as form data.

Request Body

Overview

model

• Type: string
• Required
• Description: The ID of the ASR model to use.
• Options: Ming-3.0-asr-tiny

file

• Type: file
• Required
• Description: The audio file to transcribe.
• Supported formats: .wav, .mp3
• Limits: file size ≤ 10 MB, audio duration ≤ 30 seconds

language

• Type: string
• Optional
• Description: A hint for the primary language spoken in the audio. If omitted, mixed-language recognition is enabled.

prompt

• Type: string
• Optional
• Description: In long-text scenarios, provide the previous transcription result as context to improve continuity. Recommended length is less than 60 characters.

response_format

• Type: string
• Optional, default json
• Description: The format of the transcription result.
• Options: json

temperature

• Type: number
• Optional
• Description: The sampling temperature, between 0 and 1. Lower values produce more deterministic transcriptions.

Unsupported Parameters

The following OpenAI audio/transcriptions parameters are not supported by this interface:

• chunking_strategy
• include
• keywords
• known_speaker_names
• known_speaker_references
• languages
• timestamp_granularities
• stream

Response Body

The response follows the OpenAI audio/transcriptions protocol Transcription object.

text

• Type: string
• Description: The complete transcribed text.

usage

• Type: object
• Description: Token usage statistics for the request.

usage.input_tokens

• Type: integer
• Description: Number of input tokens consumed, including audio and text tokens.

usage.output_tokens

• Type: integer
• Description: Number of output tokens generated.

usage.total_tokens

• Type: integer
• Description: Total number of tokens consumed (input_tokens + output_tokens).

usage.input_token_details

• Type: object
• Description: Breakdown of input tokens.
• Fields:
  • audio_tokens — Number of tokens consumed by the audio input.
  • text_tokens — Number of tokens consumed by the text input (such as prompt).

model

• Type: string
• Description: The ID of the model used for this request.

id

• Type: string
• Description: The unique identifier of this transcription request.

Example

Request Example

curl --request POST \
  --url https://api.ant-ling.com/v1/audio/transcriptions \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --form 'model="Ming-3.0-asr-tiny"' \
  --form 'file=@"/path/to/hellow.wav"'

from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.ant-ling.com/v1",
    api_key="<YOUR_API_KEY>"
)
 
response = client.audio.transcriptions.create(
    model="Ming-3.0-asr-tiny",
    file=open("/path/to/hellow.wav", "rb")
)
 
print(response.text)

import OpenAI from 'openai';
import fs from 'fs';
 
const client = new OpenAI({
  baseURL: 'https://api.ant-ling.com/v1',
  apiKey: '<YOUR_API_KEY>',
});
 
const response = await client.audio.transcriptions.create({
  model: 'Ming-3.0-asr-tiny',
  file: fs.createReadStream('/path/to/hellow.wav'),
});
 
console.log(response.text);

Response Example

{
  "text": "Our vision is to build the digital infrastructure of the future service industry and bring more small and beautiful changes to the world",
  "usage": {
    "input_tokens": 223,
    "output_tokens": 20,
    "total_tokens": 243,
    "type": "tokens",
    "input_token_details": {
      "audio_tokens": 218,
      "text_tokens": 5
    }
  },
  "model": "Ming-3.0-asr-tiny",
  "id": "1eef022e1790004326841103485411"
}