Qwen3-ASR 1.7B qwen3-asr-1.7b

Qwen's speech recognition model for 30 languages and 22 Chinese dialects, singing included.

From the live catalog

Input

$0.0000075 / second

region ATL quantization bf16 Hugging Face Qwen/Qwen3-ASR-1.7B

Limits

What one subscription may send this model. Limits says what happens past them.

Requests a minute	At once
30	5

Inputs

Input	Accepts
`audio`	sources base64 formats wav, mpeg max length 14K seconds max size 25 MB

Parameters

Streams with stream: true.

Parameter	Type	Values
`language`	any
`prompt`	any
`temperature`	number	0–1
`response_format`	string	json, text

Endpoints

POST/v1/audio/transcriptions Create Transcription

A request

curl https://api.vultrinference.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-asr-1.7b",
    "input_audio": {
      "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAgD4AAAB9AAACABAAZGF0YQAAAAA=",
      "format": "wav"
    },
    "language": "en"
  }'

import os
import requests

response = requests.post(
    "https://api.vultrinference.com/v1/audio/transcriptions",
    headers={"Authorization": f"Bearer {os.environ['VULTR_INFERENCE_API_KEY']}"},
    json={
        "model": "qwen3-asr-1.7b",
        "input_audio": {
            "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAgD4AAAB9AAACABAAZGF0YQAAAAA=",
            "format": "wav",
        },
        "language": "en",
    },
)
print(response.json())

const response = await fetch("https://api.vultrinference.com/v1/audio/transcriptions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VULTR_INFERENCE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "qwen3-asr-1.7b",
    "input_audio": {
      "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAgD4AAAB9AAACABAAZGF0YQAAAAA=",
      "format": "wav"
    },
    "language": "en"
  }),
});
console.log(await response.json());