alicloud-ai-audio-asr

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Category: provider

Model Studio Qwen ASR (Non-Realtime)

Model Studio Qwen ASR（非实时）

Use Qwen ASR for recorded audio transcription (non-realtime), including short audio sync calls and long audio async jobs.

可使用Qwen ASR实现录制音频的非实时转写，包括短音频同步调用和长音频异步任务。

Critical model names

关键模型名称

Use one of these exact model strings:

```
qwen3-asr-flash
```
```
qwen-audio-asr
```
```
qwen3-asr-flash-filetrans
```

Selection guidance:

Use
```
qwen3-asr-flash
```
or
```
qwen-audio-asr
```
for short/normal recordings (sync).
Use
```
qwen3-asr-flash-filetrans
```
for long-file transcription (async task workflow).

请使用以下精确的模型字符串之一：

```
qwen3-asr-flash
```
```
qwen-audio-asr
```
```
qwen3-asr-flash-filetrans
```

选型指引：

短/常规录音（同步场景）请使用
```
qwen3-asr-flash
```
或
```
qwen-audio-asr
```
。
长文件转写（异步任务流程）请使用
```
qwen3-asr-flash-filetrans
```
。

Prerequisites

前置条件

Install SDK dependencies (script uses Python stdlib only):

bash

python3 -m venv .venv
. .venv/bin/activate

Set

DASHSCOPE_API_KEY

in environment, or add

dashscope_api_key

~/.alibabacloud/credentials

安装SDK依赖（本脚本仅使用Python标准库）：

bash

python3 -m venv .venv
. .venv/bin/activate

在环境变量中设置

DASHSCOPE_API_KEY

，或者将

dashscope_api_key

添加到

~/.alibabacloud/credentials

文件中。

Normalized interface (asr.transcribe)

标准化接口（asr.transcribe）

Request

请求参数

```
audio
```
(string, required): public URL or local file path.
```
model
```
(string, optional): default
```
qwen3-asr-flash
```
.
```
language_hints
```
(array<string>, optional): e.g.
```
zh
```
,
```
en
```
.
```
sample_rate
```
(number, optional)
```
vocabulary_id
```
(string, optional)
```
disfluency_removal_enabled
```
(bool, optional)
```
timestamp_granularities
```
(array<string>, optional): e.g.
```
sentence
```
.
```
async
```
(bool, optional): default false for sync models, true for
```
qwen3-asr-flash-filetrans
```
.

```
audio
```
（字符串，必填）：公网URL或本地文件路径。
```
model
```
（字符串，可选）：默认值为
```
qwen3-asr-flash
```
。
```
language_hints
```
（字符串数组，可选）：例如
```
zh
```
、
```
en
```
。
```
sample_rate
```
（数字，可选）
```
vocabulary_id
```
（字符串，可选）
```
disfluency_removal_enabled
```
（布尔值，可选）
```
timestamp_granularities
```
（字符串数组，可选）：例如
```
sentence
```
。
```
async
```
（布尔值，可选）：同步模型默认值为false，
```
qwen3-asr-flash-filetrans
```
默认值为true。

Response

响应参数

```
text
```
(string): normalized transcript text.
```
task_id
```
(string, optional): present for async submission.
```
status
```
(string):
```
SUCCEEDED
```
or submission status.
```
raw
```
(object): original API response.

```
text
```
（字符串）：标准化后的转录文本。
```
task_id
```
（字符串，可选）：异步提交时返回。
```
status
```
（字符串）：
```
SUCCEEDED
```
或提交状态。
```
raw
```
（对象）：原始API响应。

Quick start (official HTTP API)

快速上手（官方HTTP API）

Sync transcription (OpenAI-compatible protocol):

bash

curl -sS --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "qwen3-asr-flash",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_audio",
            "input_audio": {
              "data": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
            }
          }
        ]
      }
    ],
    "stream": false,
    "asr_options": {
      "enable_itn": false
    }
  }'

Async long-file transcription (DashScope protocol):

bash

curl -sS --location 'https://dashscope.aliyuncs.com/api/v1/services/audio/asr/transcription' \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --header 'X-DashScope-Async: enable' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "qwen3-asr-flash-filetrans",
    "input": {
      "file_url": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
    }
  }'

Poll task result:

bash

curl -sS --location "https://dashscope.aliyuncs.com/api/v1/tasks/<task_id>" \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY"

同步转写（兼容OpenAI协议）：

bash

curl -sS --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "qwen3-asr-flash",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_audio",
            "input_audio": {
              "data": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
            }
          }
        ]
      }
    ],
    "stream": false,
    "asr_options": {
      "enable_itn": false
    }
  }'

异步长文件转写（DashScope协议）：

bash

curl -sS --location 'https://dashscope.aliyuncs.com/api/v1/services/audio/asr/transcription' \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --header 'X-DashScope-Async: enable' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "qwen3-asr-flash-filetrans",
    "input": {
      "file_url": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
    }
  }'

轮询任务结果：

bash

curl -sS --location "https://dashscope.aliyuncs.com/api/v1/tasks/<task_id>" \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY"

Local helper script

本地辅助脚本

Use the bundled script for URL/local-file input and optional async polling:

bash

python skills/ai/audio/alicloud-ai-audio-asr/scripts/transcribe_audio.py \
  --audio "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3" \
  --model qwen3-asr-flash \
  --language-hints zh,en \
  --print-response

Long-file mode:

bash

python skills/ai/audio/alicloud-ai-audio-asr/scripts/transcribe_audio.py \
  --audio "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3" \
  --model qwen3-asr-flash-filetrans \
  --async \
  --wait

可使用附带的脚本处理URL/本地文件输入，也支持可选的异步轮询功能：

bash

python skills/ai/audio/alicloud-ai-audio-asr/scripts/transcribe_audio.py \
  --audio "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3" \
  --model qwen3-asr-flash \
  --language-hints zh,en \
  --print-response

长文件模式：

bash

python skills/ai/audio/alicloud-ai-audio-asr/scripts/transcribe_audio.py \
  --audio "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3" \
  --model qwen3-asr-flash-filetrans \
  --async \
  --wait

Operational guidance

操作指引

For local files, use
```
input_audio.data
```
(data URI) when direct URL is unavailable.
Keep
```
language_hints
```
minimal to reduce recognition ambiguity.
For async tasks, use 5-20s polling interval with max retry guard.
Save normalized outputs under
```
output/ai-audio-asr/transcripts/
```
.

没有直接可用的URL时，本地文件可使用
```
input_audio.data
```
（数据URI）格式。
尽量精简
```
language_hints
```
配置，以降低识别歧义。
异步任务建议使用5-20秒的轮询间隔，同时设置最大重试保护。
标准化输出请保存到
```
output/ai-audio-asr/transcripts/
```
目录下。

Output location

输出位置

Default output:
```
output/ai-audio-asr/transcripts/
```
Override base dir with
```
OUTPUT_DIR
```
.

默认输出路径：
```
output/ai-audio-asr/transcripts/
```
可通过
```
OUTPUT_DIR
```
环境变量覆盖基础目录。

References

参考资料

```
references/api_reference.md
```
```
references/sources.md
```

Realtime synthesis is provided by

skills/ai/audio/alicloud-ai-audio-tts-realtime/

```
references/api_reference.md
```
```
references/sources.md
```

实时语音合成能力由

skills/ai/audio/alicloud-ai-audio-tts-realtime/

提供。