Alibaba · Qwen · Speech alignment
Qwen3 Forced Alignment
Aligns an existing transcript to speech and returns precise word-level timestamps.
qwenasr-alignCurrent model-specific price from our catalog. Requests require your project API key and sufficient balance. Availability is checked at execution time.
Input and capabilities
Upload a short audio or video file using multipart/form-data: at most 30 seconds and 20 MiB. Use WAV for the examples below. Container compatibility depends on the model.
- transcription
- word timestamps
- alignment
Automatic language detection: not supported.
Supported language codes: zh-CN, en, yue, fr, de, it, ja, ko, pt, ru, es.
API endpoint
POST https://api.speechinfra.com/v1/inference/qwenasr-align
Authenticate with your Speechinfra project key. Read the quickstart and billing guide.
cURL
curl --fail-with-body "https://api.speechinfra.com/v1/inference/qwenasr-align" \
-H "Authorization: Bearer $SPEECH_API_KEY" \
-F "file=@clip.wav" \
--form-string "language=en" \
--form-string "transcript=Verbatim transcript matching the clip"Python
# pip install httpx
import os
import httpx
headers = {"Authorization": "Bearer " + os.environ["SPEECH_API_KEY"]}
with open("clip.wav", "rb") as audio:
response = httpx.post(
"https://api.speechinfra.com/v1/inference/qwenasr-align",
headers=headers, files={"file": ("clip.wav", audio, "audio/wav")},
data={
"language": "en",
"transcript": "Verbatim transcript matching the clip"
}, timeout=90,
)
response.raise_for_status()
print(response.json())Node.js / fetch
// Node.js 22+, no SDK required.
import { readFile } from 'node:fs/promises';
const form = new FormData();
form.set('file', new Blob([await readFile('clip.wav')]), 'clip.wav');
for (const [key, value] of Object.entries({
"language": "en",
"transcript": "Verbatim transcript matching the clip"
})) form.set(key, value);
const response = await fetch("https://api.speechinfra.com/v1/inference/qwenasr-align", {
method: 'POST', body: form, signal: AbortSignal.timeout(90000),
headers: { Authorization: 'Bearer ' + process.env.SPEECH_API_KEY },
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());Request parameters
Generated from the API schema for this deployment. Conditional parameters apply only when their controlling setting is enabled.
| Parameter | Type | Details |
|---|---|---|
fileRequired | string | Short audio or video file. Direct API limit: 30 seconds, 20 MiB. |
language | string | enum: zh-CN, en, yue, fr, de, it, ja, ko, pt, ru, es · default: "en" All accepted values[ "zh-CN", "en", "yue", "fr", "de", "it", "ja", "ko", "pt", "ru", "es" ] |
transcriptRequired | string | Verbatim transcript of the uploaded clip. max 20000 chars |
Complete request schema
{
"type": "object",
"additionalProperties": false,
"required": [
"file",
"transcript"
],
"properties": {
"file": {
"type": "string",
"format": "binary",
"description": "Short audio or video file. Direct API limit: 30 seconds, 20 MiB."
},
"language": {
"type": "string",
"default": "en",
"enum": [
"zh-CN",
"en",
"yue",
"fr",
"de",
"it",
"ja",
"ko",
"pt",
"ru",
"es"
]
},
"transcript": {
"type": "string",
"minLength": 1,
"maxLength": 20000,
"description": "Verbatim transcript of the uploaded clip."
}
}
}Response schema
The schema below describes the response; optional fields depend on model settings.
View complete response schema
{
"$defs": {
"Word": {
"properties": {
"word": {
"title": "Word",
"type": "string"
},
"start": {
"title": "Start",
"type": "number"
},
"end": {
"title": "End",
"type": "number"
},
"confidence": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Confidence"
},
"speaker": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Speaker"
}
},
"required": [
"word",
"start",
"end"
],
"title": "Word",
"type": "object"
}
},
"properties": {
"words": {
"items": {
"$ref": "#/$defs/Word"
},
"title": "Words",
"type": "array"
},
"language": {
"title": "Language",
"type": "string"
},
"model": {
"default": "qwen3-forced-aligner-0.6b",
"title": "Model",
"type": "string"
}
},
"required": [
"words",
"language"
],
"title": "AlignmentResult",
"type": "object"
}