Non-real-time speech recognition (Qwen-Audio-ASR) HTTP API

For input requirements such as supported audio formats, file size limits, and duration limits, see Audio specifications.

Service endpoints

Singapore
China (Beijing)

POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generationReplace {WorkspaceId} with your actual Workspace ID.

Alibaba Cloud Model Studio has released workspace-specific domains for the China (Beijing) and Singapore regions. The new dedicated domains deliver superior performance and higher stability for inference requests. We recommend migrating to the new domains:

China (Beijing): from dashscope.aliyuncs.com to {WorkspaceId}.cn-beijing.maas.aliyuncs.com
Singapore: from dashscope-intl.aliyuncs.com to {WorkspaceId}.ap-southeast-1.maas.aliyuncs.com

Request headers

Parameter	Type	Required	Description
`Authorization`	`string`	Yes	The authentication token, in the format `Bearer <your_api_key>`. Replace "`<your_api_key>`" with your actual API key.
`Content-Type`	`string`	Yes	The media type of the request body. Fixed to `application/json`.
`X-DashScope-SSE`	`string`	No	Controls whether to request streaming results. Set to `enable` to request SSE streaming. Set to `disable` or omit this parameter to return only the final result. Applies only to `qwen-audio-3.0-asr-flash`: SSE streaming is available only for audio that is at least 1 minute long.

Request body

modelstring(Required)The model name.inputobject(Required)The input information.

Properties

messagesarray(object)(Required)The message list. It contains the audio to recognize and, optionally, conversation context that improves recognition accuracy.

The context feature improves the recognition accuracy of domain-specific terms. For usage, see Context enhancement.A request can include at most 5 context messages of each type (input_text and text). If you exceed this limit, only the 5 most recent messages are kept. The total context text per turn (the combined length of the text fields in the user and assistant messages) cannot exceed 400 characters, where each character counts as 1. Any excess is truncated from the end.

When you include context, the message order in messages matters: context messages must be arranged by conversation turn. Within each turn, the user message (of type input_text) must come before the corresponding assistant message (of type text). The user message that contains input_audio must be the last item in the messages array.

Properties

rolestring(Required)The message role. Valid values:

user (Required): A user message. When type is input_audio, it holds the audio to recognize. When type is input_text, it holds recognition results from previous turns or a domain-specific word list (optional, used as context).
assistant (Optional, context): Replies from the large language model in previous turns.

contentarray(object)(Required)The message content list.

Properties

typestring(Required)The content type. Each request needs at least one message of type input_audio. Valid values:

input_audio (Required): The audio input to recognize (role is user). You must also pass the input_audio object.
input_text (Optional, context): Recognition results of the user's speech from previous turns, or a domain-specific word list (role is user). You must also pass the text field.
text (Optional, context): Replies from the large language model in previous turns (role is assistant). You must also pass the text field.

input_audioobject(Conditionally required)Required when type is input_audio.

Properties

datastring(Required)The audio data to recognize. For input requirements such as supported audio formats, file size limits, and duration limits, see Audio specifications. Two methods are supported:

Audio file URL: Pass a publicly accessible URL to the audio file.
Base64 Data URI: Pass the Base64-encoded audio data as a Data URI. The value is the data:{MIME_TYPE};base64, prefix concatenated with the Base64-encoded audio data. Supported MIME types include audio/wav and audio/mp3.

Example (URL): https://example.com/audio/sample.wavExample (Base64): data:audio/wav;base64,{BASE64_ENCODED_DATA}

textstring(Conditionally required)When type is input_text, enter the recognition results of the user's speech from previous turns or a domain-specific word list. When type is text, enter the large language model's replies from previous turns. Text length is measured in characters, where each character counts as 1. The combined length of the text fields across all messages in a single context turn cannot exceed 400 characters. Any excess is truncated from the end.

parametersobject(Required)The model parameters.

Text polishing is disabled by default and is not yet available for qwen-audio-3.0-asr-flash. qwen-audio-3.1-asr-flash supports native text polishing.Text polishing: While transcribing speech, the model removes meaningless filler words and stuttered repetitions, handles self-corrections, smooths out colloquial expressions, and standardizes punctuation and text formatting. The output is more concise, fluent, and readable while preserving the speaker’s final intent and key information as much as possible.

Properties

speaker_diarization_enabled boolean (Optional)

Applies only to qwen-audio-3.1-asr-flash.

Specifies whether to enable speaker diarization. Default: false. When set to true, the response uses speaker_id to distinguish speakers and includes output.sentences. When diarization is enabled, keep_dialect and language_hints are ignored.keep_dialect boolean (Optional)

Applies only to qwen-audio-3.1-asr-flash.

Specifies whether to preserve dialect expressions. Default: false. Set to false to transcribe dialect speech as standard Mandarin text, or true to preserve dialect expressions.formatstring(Required)The audio format. Set this to match your actual audio format. Supported values include wav, mp3, and opus. For details, see Audio specifications.sample_ratestring(Optional)The audio sample rate, in Hz. For example, 16000 means a 16 kHz sample rate. For details, see Audio specifications.vocabulary_idstring(Optional)The ID of a precompiled hot word list.Generate this ID in advance by calling the create hot word list API. Pass the ID during recognition to use the hot words in the list.Suitable for scenarios where the vocabulary is known and relatively stable, and where you need to reuse the same word list across requests.For usage details, see Precompiled hotwords.vocabularyobject(Optional)Instant hot words.Passed as key-value pairs, where the key is the hot word text (string) and the value is the hot word weight (integer). No hot word list needs to be created in advance. The weight ranges from [1, 5] or is set to 50: a value in [1, 5] makes the model more likely to output the word as the value increases; a value of 50 designates a super hot word, which greatly improves recall, but the number of super hot words cannot exceed 50.Suitable for temporary, session-level hot word optimization.When instant and precompiled hotwords are configured together, the system merges both sets. If the merged set contains more than 2000 hotwords, the system randomly selects 2000 to use. For usage details, see Instant hotwords.language_hints array[string](Optional)The language codes to recognize. If the language is unknown in advance, omit this parameter to let the model detect it automatically. You can set up to 4 values. If you set more, only the first 4 take effect.Specifying language codes can improve recognition accuracy.

Supported language codes

zh: Chinese
en: English
ja: Japanese
ko: Korean
vi: Vietnamese
th: Thai
id: Indonesian
ms: Malay
tl: Filipino
hi: Hindi
ar: Arabic
fr: French
de: German
es: Spanish
pt: Portuguese
ru: Russian
it: Italian
nl: Dutch
sv: Swedish
da: Danish
fi: Finnish
no: Norwegian
el: Greek
pl: Polish
cs: Czech
hu: Hungarian
ro: Romanian
bg: Bulgarian
hr: Croatian
sk: Slovak

qwen-audio-3.1-asr-flash also supports the following language codes:

tr: Turkish
fa: Persian
mr: Marathi
ml: Malayalam
ne: Nepali
ky: Kyrgyz
az: Azerbaijani
ka: Georgian
hy: Armenian
sl: Slovenian
sq: Albanian
et: Estonian
lv: Latvian
lt: Lithuanian
ca: Catalan
eu: Basque
gl: Galician
or: Odia
dv: Divehi
as: Assamese
ku: Kurdish
tig: Tigre
fy: Western Frisian
ba: Bashkir
be: Belarusian
tt: Tatar
ia: Interlingua
mhr: Eastern Mari
tok: Toki Pona

The following examples use the configuration for the Singapore region. Replace "{WorkspaceId}" with your actual workspace ID. The configuration differs across regions, and the API key for the Singapore region differs from the one for the Beijing region.

curl --location --request POST 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
     --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
     --header "Content-Type: application/json" \
     --header "X-DashScope-SSE: disable" \
     --data '{
    "model": "qwen-audio-3.1-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "{YOUR_AUDIO_URL}"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000"
    }
}'

curl --location --request POST 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
     --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
     --header "Content-Type: application/json" \
     --header "X-DashScope-SSE: enable" \
     --data '{
    "model": "qwen-audio-3.1-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "{YOUR_AUDIO_URL}"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000"
    }
}'

curl --location --request POST 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
     --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
     --header "Content-Type: application/json" \
     --header "X-DashScope-SSE: disable" \
     --data @- <<'JSON'
{
    "model": "qwen-audio-3.1-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_text",
                        "text": "Hello"
                    }
                ]
            },
            {
                "role": "assistant",
                "content": [
                    {
                        "type": "text",
                        "text": "Hello, I'm Qwen. How can I help you?"
                    }
                ]
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "{YOUR_AUDIO_URL}"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000"
    }
}
JSON

curl --location --request POST 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
     --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
     --header "Content-Type: application/json" \
     --header "X-DashScope-SSE: enable" \
     --data @- <<'JSON'
{
    "model": "qwen-audio-3.1-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_text",
                        "text": "Hello"
                    }
                ]
            },
            {
                "role": "assistant",
                "content": [
                    {
                        "type": "text",
                        "text": "Hello, I'm Qwen. How can I help you?"
                    }
                ]
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "{YOUR_AUDIO_URL}"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000"
    }
}
JSON

You can pass Base64-encoded data (Data URL) in the format data:<mediatype>;base64,<data>.

<mediatype>: The MIME type. The value depends on the audio format. For example:
- WAV: audio/wav
- MP3: audio/mpeg
<data>: The Base64-encoded string of the audio. Base64 encoding increases the data size. For audio file size and duration limits, see Audio specifications.

Example: data:audio/wav;base64,SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4LjI5LjEwMAAAAAAAAAAAAAAA//PAxABQ/BXRbMPe4IQAhl9

import base64, pathlib

# Replace with the path to your own audio file and make sure it meets the audio requirements
file_path = pathlib.Path("{YOUR_AUDIO_FILE}")
base64_str = base64.b64encode(file_path.read_bytes()).decode()
data_uri = f"data:audio/mpeg;base64,{base64_str}"

import base64, pathlib
import os
import requests

# Replace with the path to your own audio file and make sure it meets the audio requirements
file_path = pathlib.Path("{YOUR_AUDIO_FILE}")
base64_str = base64.b64encode(file_path.read_bytes()).decode()
data_uri = f"data:audio/wav;base64,{base64_str}"

# Replace "{WorkspaceId}" with your actual workspace ID
url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation"

headers = {
    "Authorization": f"Bearer {os.environ['DASHSCOPE_API_KEY']}",
    "Content-Type": "application/json",
    "X-DashScope-SSE": "disable",
}

payload = {
    "model": "qwen-audio-3.1-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": data_uri,
                        },
                    }
                ],
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000",
    },
}

response = requests.post(url, headers=headers, json=payload)
print(response.status_code)
print(response.json())

curl --location --request POST 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
     --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
     --header "Content-Type: application/json" \
     --header "X-DashScope-SSE: disable" \
     --data '{
    "model": "qwen-audio-3.1-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "{YOUR_AUDIO_URL}"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000",
        "vocabulary": {"John Smith": 5, "Jane Doe": 5}
    }
}'

Response body

request_idstringThe unique identifier of this request.outputobjectThe output result.

Properties

textstringThe full recognized text accumulated so far.sentences array[object]

Applies only to qwen-audio-3.1-asr-flash.

Returned when speaker diarization is enabled. Contains recognition results for the current and previous sentences. Each element has the same structure as sentence.sentenceobjectThe details of the current sentence.

Properties

speaker_id integer | null

Applies only to qwen-audio-3.1-asr-flash.

The speaker ID, used to distinguish speakers. Contains an ID when speaker diarization is enabled, and is null otherwise.sentence_idintegerThe sentence number, starting from 1.sentence_endbooleanWhether this is the final result for the sentence. true indicates that recognition of the sentence is complete.begin_timeintegerThe start time of the sentence, in milliseconds.end_timeintegerThe end time of the sentence, in milliseconds. Returned only when sentence_end is true.textstringThe recognized text of the current sentence.channel_idintegerThe channel number, starting from 0.wordsarrayThe list of word-level timestamps.

Properties

speaker_id integer | null

Applies only to qwen-audio-3.1-asr-flash.

The ID of the speaker for this word. Contains an ID when speaker diarization is enabled, and is null otherwise.textstringThe word text.begin_timeintegerThe start time of the word, in milliseconds.end_timeintegerThe end time of the word, in milliseconds.punctuationstringThe punctuation mark after the word. An empty string when there is no punctuation.fixedbooleanWhether the word is stabilized. false indicates that the word's timestamp may be adjusted in subsequent events.

usageobjectThe usage information. Returned only when sentence_end is true.

Properties

durationintegerThe processed audio duration, in seconds.input_tokens integer

Applies only to qwen-audio-3.1-asr-flash.

The number of input tokens consumed by this request.output_tokens integer

Applies only to qwen-audio-3.1-asr-flash.

The number of output tokens consumed by this request.total_tokens integer

Applies only to qwen-audio-3.1-asr-flash.

The total number of tokens consumed by this request, equal to the sum of input_tokens and output_tokens.

Non-streaming
Streaming

{
    "output": {
        "sentence": {
            "begin_time": 760,
            "channel_id": 0,
            "end_time": 3800,
            "sentence_end": true,
            "sentence_id": 1,
            "text": "Hello World, this is Alibaba Speech Lab.",
            "words": [
                {"begin_time": 760, "end_time": 1040, "fixed": true, "punctuation": "", "text": "Hello"},
                {"begin_time": 1040, "end_time": 1240, "fixed": true, "punctuation": ",", "text": " World"},
                {"begin_time": 1360, "end_time": 1880, "fixed": true, "punctuation": "", "text": "this is"},
                {"begin_time": 1880, "end_time": 2520, "fixed": true, "punctuation": "", "text": "Alibaba"},
                {"begin_time": 2520, "end_time": 2840, "fixed": true, "punctuation": "", "text": "Speech"},
                {"begin_time": 2840, "end_time": 3800, "fixed": true, "punctuation": ".", "text": "Lab"}
            ]
        },
        "text": "Hello World, this is Alibaba Speech Lab."
    },
    "usage": {
        "duration": 4
    },
    "request_id": "40e0734d-096f-9ae3-86c1-a8c013287561"
}

The SSE streaming response uses the following event format:

id:{sequence_number}
      event:result
      :HTTP_STATUS/200
      data:{JSON_data}

Example response:

id:1
event:result
:HTTP_STATUS/200
data:{"output":{"sentence":{"sentence_id":1,"sentence_end":true,"end_time":3800,"words":[{"end_time":1040,"punctuation":"","begin_time":760,"fixed":true,"text":"Hello"},{"end_time":1240,"punctuation":",","begin_time":1040,"fixed":true,"text":" World"},{"end_time":1880,"punctuation":"","begin_time":1360,"fixed":true,"text":"this is"},{"end_time":2520,"punctuation":"","begin_time":1880,"fixed":true,"text":"Alibaba"},{"end_time":2840,"punctuation":"","begin_time":2520,"fixed":true,"text":"Speech"},{"end_time":3800,"punctuation":".","begin_time":2840,"fixed":true,"text":"Lab"}],"begin_time":760,"text":"Hello World, this is Alibaba Speech Lab.","channel_id":0},"text":"Hello World, this is Alibaba Speech Lab."},"usage":{"duration":4},"request_id":"fc1582e4-935c-9fc2-a482-a98bf43daa69"}

SSE streaming result processing logic

In streaming mode, the client needs to handle the following:

For each SSE event received, parse the JSON in the data field.
For qwen-audio-3.0-asr-flash, use output.sentence.sentence_end to determine whether the current sentence has ended. When it is true, recognition is complete, the word-level timestamps are stabilized, and the result can be used as final. When it is false, recognition is still in progress, and text and timestamps may be updated in subsequent events.
The usage information is returned only in sentence-end events and includes the processed audio duration. For qwen-audio-3.1-asr-flash, it also includes the input, output, and total token counts for the request. This model is billed by token usage.

For qwen-audio-3.1-asr-flash without speaker diarization, a word timestamp becomes final only when output.sentence.words[i].fixed is true. Until then, timestamps may change. When speaker diarization is enabled, read the current and previous sentence results from output.sentences.

​Service endpoints

​Request headers

Request body

Response body

​SSE streaming result processing logic

Service endpoints

Request headers

SSE streaming result processing logic