Qwen-Audio-ASR-Message Node.js SDK - Alibaba Cloud Model Studio

Use the speech Node.js SDK to call Qwen-Audio-ASR-Message, handle recognition results, and update context during a task.

Install the SDK

Requires Node.js 18 or later. Download the SDK 0.1.0 package, then run this command in your project:

npm install ./dashscope-sdk-nodejs-0.1.0.tgz

Quick start

Obtain an API key in the console and set it as the DASHSCOPE_API_KEY environment variable.

Download the sample audio as input.mp3 and convert it to 16 kHz, 16-bit, mono PCM:

ffmpeg -i input.mp3 -f s16le -ac 1 -ar 16000 input.pcm

Save the following example as example.mjs and run node example.mjs.

import { readFile } from 'node:fs/promises'
import { setTimeout as sleep } from 'node:timers/promises'
import { RecognitionClient } from 'dashscope-sdk-nodejs/asr'

const pcm = await readFile('input.pcm')
const asr = new RecognitionClient({
  apiKey: process.env.DASHSCOPE_API_KEY,
  workspaceId: process.env.DASHSCOPE_WORKSPACE_ID,
  baseUrl: 'dashscope-intl.aliyuncs.com',
  model: 'qwen-audio-3.1-asr-flash-message',
  format: 'pcm',
  sampleRate: 16000,
})
asr.on('sentenceEnd', sentence => console.log('Final sentence:', sentence.text))
asr.on('error', err => console.error(err.code, err.message))

try {
  await asr.start()
  for (let offset = 0; offset < pcm.length; offset += 3200) {
    asr.sendAudio(pcm.subarray(offset, offset + 3200))
    await sleep(100)
  }
  await asr.finish()
} finally {
  asr.close()
}

API reference

Constructor options

Constructor options for RecognitionClient:

Parameter	Type	Required	Description
`apiKey`	`string`	No	API key. Defaults to `DASHSCOPE_API_KEY`.
`workspaceId`	`string`	No	Workspace ID. Defaults to `DASHSCOPE_WORKSPACE_ID`.
`baseUrl`	`string`	No	Set the service hostname to `dashscope-intl.aliyuncs.com` (Singapore).
`model`	`string`	Yes	Set the model ID to `qwen-audio-3.1-asr-flash-message`.
`format`	`'pcm' \| 'wav' \| 'mp3' \| 'opus' \| 'speex' \| 'aac' \| 'amr'`	No	Audio format. Default: `pcm`. WAV uses PCM encoding, Opus/Speex use Ogg containers, and AMR uses AMR-NB.
`sampleRate`	`number`	No	Audio sample rate. Use `16000` Hz.
`vocabularyId`	`string`	No	Precompiled vocabulary ID.
`languageHints`	`string[]`	No	Recognition language hints. Up to the first 4 values take effect. Language is detected automatically if omitted.
`disfluencyRemovalEnabled`	`boolean`	No	Remove disfluencies and polish results. Default: `false`.
`maxSentenceSilence`	`number`	No	VAD sentence-ending silence threshold in ms: `[200,6000]`; default: `800`.
`heartbeat`	`boolean`	No	Silence keepalive. Default: `false`; keep sending silent audio when enabled.
`context`	`AsrContextMessage[]`	No	Recognition context. Message format: `{ role, content: [{ type: "input_text", text }] }`, with `role` set to `user` or `assistant`. Up to 5 messages per role and fewer than 400 characters in total, ordered by conversation turn.
`parameters`	`Partial<RecognitionParameters>`	No	Additional recognition parameters, such as `vad_model`, `keep_dialect`, and `vocabulary`.
`connectTimeoutMs`	`number`	No	Connection timeout in ms. Default: `10000`.
`taskTimeoutMs`	`number`	No	Start/finish acknowledgement timeout in ms. Default: `60000`; `0` disables the timeout.
`parameters.vad_model`	`'near_meeting_16k' \| 'far_field_meeting_16k'`	No	Near-field or far-field VAD. Default: `far_field_meeting_16k`.
`parameters.keep_dialect`	`boolean`	No	Preserve dialect expressions. Default: `false`.
`parameters.vocabulary`	`Record<string, number>`	No	Instant vocabulary: words as keys and weights in `[1,5]` or `50` as values.
`parameters.speech_noise_threshold`	`number`	No	VAD sensitivity threshold: `[-1,1]`.
`parameters.intermediate_result_enabled`	`boolean`	No	Return intermediate recognition results. Default: `false`.

Main methods

Method	Return value	Description
`start()`	`Promise<void>`	Start recognition; send audio after it resolves.
`sendAudio(audio: Buffer \| Uint8Array)`	`void`	Send audio frames in the configured format and sample rate.
`updateContext(context: AsrContextMessage[])`	`void`	Update recognition context after starting and before finishing input.
`finish()`	`Promise<void>`	Finish audio input and wait for completion. Text arrives through callbacks.
`close(code?: number, reason?: string)`	`void`	Close the connection and release task resources.

Callback events

Event	Payload	Description
`started`	`{ taskId: string }`	Task has started and accepts input.
`result`	`{ text: string; sentence_end: boolean; sentence_begin?: boolean; words?: RecognitionWord[] }`	Intermediate or final sentence, excluding heartbeat results.
`sentenceEnd`	`{ text: string; sentence_end: boolean; sentence_begin?: boolean; words?: RecognitionWord[] }`	Final sentence with `sentence_end === true`.
`finished`	`{ taskId: string; duration?: number; usage?: RecognitionUsage }`	Task has finished and local task state is cleared.
`failed / error`	`DashScopeError`	Call error with `code`, `message`, and request identifiers.
`close`	`{ code: number; reason: string }`	Underlying connection-close notification.
`event`	`ServerEvent`	Raw service JSON message.