CreateTask - Create a real-time meeting minutes task

Prerequisites

Activate the service and obtain and configure an API key. To prevent security risks from code leaks, configure the API key as an environment variable instead of hard coding it in your code.

To grant temporary access permissions to third-party applications or users, or want to strictly control risky operations such as accessing or deleting sensitive data, you can use a temporary authentication token.Compared to a long-term API key, a temporary authentication token is valid for only a short period (60 seconds) and offers higher security. It is suitable for temporary call scenarios and can effectively reduce the risk of API key leaks.Usage: In your code, replace the API key used for authentication with the obtained temporary authentication token.

Overall call flow

For more information, see Real-time meetings.

Endpoint

https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation

Request method

POST method

Request headers

Authorization: Bearer sk-xxxxxxxxxxxxxx
Content-Type: application/json

Replace the value of Authorization with your actual API key.

Request parameters

Name	Type	Required	Description	Example
model	string	Yes	The business type. Set the value to `tingwu-meeting`.	tingwu-meeting
input	object	Yes	You can pass the relevant business parameters.
input.type	string	Yes	The task type. To create a real-time meeting task, set the value to `realtime`.	realtime
input.appId	string	Yes	The application ID. You can obtain it from the application configuration page in the console.
input.task	string	Yes	The task type. Set the value to `createTask` to create a task.	createTask
input.format	string	Yes	The encoding format of the meeting audio. Valid formats: pcm, opus, aac, speex, and mp3. This parameter is required when you create a meeting. It is optional when you end a meeting and generate minutes.	pcm
input.sampleRate	int	Yes	The sample rate of the meeting audio. Valid values: 8000 and 16000. This parameter is required when you create a meeting. It is optional when you end a meeting and generate minutes.	16000
input.phraseId	string	No	The ID of the hotword list. You can obtain it from the Hotwords page in the console. This parameter is required when you create a meeting. It is optional when you end a meeting and generate minutes.
input.dataId	string	Yes	The `dataId` obtained when the meeting was created. This parameter is required when you end a meeting and generate minutes. It is optional when you create a meeting.
parameters	object	No	The control parameters for generating real-time meeting minutes. If you pass a null object, the published online configuration is used.
parameters.transcription	object	No	The transcription control parameters.
parameters.transcription.model	string	No	The transcription model. Valid values: cn (supports Chinese and English) multilingual (supports Chinese, English, Japanese, Korean, and Cantonese) en (English model) yue (Cantonese model) ja (Japanese model) ko (Korean model) domain-education (education realm model, supports Chinese and English) domain-automotive (automotive realm model, supports Chinese, English, and Cantonese)	multilingual
parameters.transcription.languageHints	array	No	This parameter takes effect only when `parameters.transcription.model` is set to `multilingual`. It specifies the possible languages in the audio. Languages not specified in this parameter will not appear in the recognition results.	["cn", "en"]
parameters.transcription.diarizationEnabled	bool	No	Specifies whether to enable speaker diarization.	true
parameters.transcription.diarizationSpeakerCount	int	No	The target number of speakers for diarization. Valid values: 0: The number of speakers is uncertain. 2: Distinguishes between two speakers. The default value is 0.	0
parameters.transcription.translationEnabled	bool	No	Specifies whether to enable translation.	true
parameters.transcription.translationTargetLang	array	No	If translation is enabled, you must set the target language. Supported target languages: cn: Chinese en: English ja: Japanese ko: Korean de: German fr (French) ru (Russian) You can select only one item at a time.	["en"]
parameters.audio	object	No	The audio parameters.
parameters.audio.audioChannelMode	string	No	The multi-channel audio configuration. Valid values: `mix`: Mixes audio channels before speaker diarization. Empty string If you pass an empty string or do not pass this parameter, the operation varies based on the audio sample rate: 16 kHz audio: Only the first channel is recognized. 8 kHz audio: Channel 1 is recognized as Speaker 1, and Channel 2 is recognized as Speaker 2.	mix
parameters.analysis	object	No	The large model analysis parameters.
parameters.analysis.model	string	No	The global analysis model. Valid values: default (default analysis model) tingwu-plus qwen-plus qwq	tingwu-plus
parameters.analysis.keyInformationEnabled	bool	No	Specifies whether to extract keywords.	true
parameters.analysis.actionsEnabled	bool	No	Specifies whether to extract action items.	true
parameters.analysis.fullSummaryEnabled	bool	No	Specifies whether to extract a full-text summary.	true
parameters.analysis.fullSummaryFormat	string	No	The format of the full-text summary. Valid values: default (Summarizes the entire text in a single paragraph.) `markdown`: A Markdown-formatted summary. This parameter takes effect only when `parameters.analysis.fullSummaryEnabled` is `true`.	default
parameters.analysis.conversationalEnabled	bool	No	Specifies whether to extract speaker summaries.	true
parameters.analysis.questionsAnsweringEnabled	bool	No	Specifies whether to extract a Q&A review (or key points review).	true
parameters.analysis.mindMapEnabled	bool	No	Specifies whether to extract a mind map.	true
parameters.analysis.mindMapFormat	string	No	The format of the extracted mind map. Valid values: `timestamp`: Includes timestamps in the mind map. `plain`: Does not include timestamps in the mind map. This parameter takes effect only when `parameters.analysis.mindMapEnabled` is `true`.	timestamp
parameters.analysis.pptExtractionEnabled	bool	No	Specifies whether to extract PPT slides and PPT summaries from the video.	true
parameters.analysis.autoChaptersEnabled	bool	No	Specifies whether to enable chapter overviews.	true
parameters.analysis.autoChapterGranularity	string	No	The granularity for extracting chapter overviews. Valid values: `Coarse`: Approximately 4 chapters per hour of audio/video. `General`: Approximately 6 chapters per hour of audio/video. `Meticulous`: Approximately 12 to 15 chapters per hour of audio/video. This parameter takes effect only when `parameters.analysis.autoChaptersEnabled` is `true`.	Coarse
parameters.analysis.autoChapterTitleLengthLevel	string	No	The length level of chapter titles. Valid values: `Short`: 6 to 25 characters, with an average of about 13 characters. `Normal`: 10 to 28 characters, with an average of about 16 characters. `Long`: 10 to 30 characters, with an average of about 20 characters. This parameter takes effect only when `parameters.analysis.autoChaptersEnabled` is `true`.	Normal
parameters.analysis.textPolishEnabled	bool	No	Specifies whether to convert spoken language to written text.	true
parameters.analysis.customPromptEnabled	bool	No	Specifies whether to enable custom prompts.	true
parameters.analysis.customPromptModel	string	No	The analysis model for custom prompts. Valid values: tingwu-turbo tingwu-plus qwen-max This parameter takes effect only when `parameters.analysis.customPromptEnabled` is `true`.	tingwu-plus
parameters.analysis.customPromptTransType	string	No	Controls how the `{Transcription}` placeholder in the prompt is replaced with text. The protocols are as follows: `default`: Transcription result only. Example: What is the weather like in Beijing? What is the weather like in Shanghai? `chat`: Speaker + transcription result. Example: Speaker 1: What is the weather like in Beijing?\nSpeaker 2: What is the weather like in Shanghai?\n `sentence-chat`: Sentence ID + speaker + result. Example: [1] Speaker 1: What is the weather like in Beijing?\n[2] Speaker 2: What is the weather like in Shanghai?\n This parameter takes effect only when `parameters.analysis.customPromptEnabled` is `true`.	chat
parameters.analysis.customPromptContent	string	No	The custom prompt. This parameter takes effect only when `parameters.analysis.customPromptEnabled` is `true`. Note: You must include the `{Transcription}` placeholder in this parameter. Tingwu automatically inserts the transcription result at the placeholder's location. If the `{Transcription}` placeholder is not set, the custom prompt feature will not work.	Please help me extract the role corresponding to each speaker ID from the original text. Possible roles include sales staff and test drive customers. The original text is as follows: {Transcription}

Response parameters

Name	Type	Description	Example
output	object
output.dataId	string	The task ID.
output.status	int	0: Completed 1: Generating minutes 2: Failed 3: Transcribing	3
usage	object	The usage. This is currently a null object.	{}
code	string	The error code.	InvalidParameter
message	string	The error message.	Agent Input text format error.
request_id	string	The request ID.	f97ee37d-0f9c-9b93-b6bf-bd263a232bf9

Request examples

Replace sk-*** in the Authorization request header with your actual Alibaba Cloud Model Studio API key.

Create a real-time meeting

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header 'Authorization: Bearer sk-******e181c' \
--header 'Content-Type: application/json' \
--data '{
    "model": "tingwu-meeting",
    "input": {
        "task": "createTask",
        "appId": "tw_***",
        "type": "realtime",
        "format": "pcm",
        "sampleRate": 16000,
        "phraseId": "DEA******Isv"
    },
    "parameters": {
        "transcription": {
          "model": "multilingual",
          "languageHints": ["cn", "en"],
          "diarizationEnabled": true,
          "diarizationSpeakerCount": 0,
          "translationEnabled": true,
          "translationTargetLang": ["ja"]
        },
        "audio": {
          "audioChannelMode": ""
        },
        "analysis": {
          "model": "default",
          "keyInformationEnabled": true,
          "actionsEnabled": false,
          "fullSummaryEnabled": true,
          "fullSummaryFormat": "default",
          "conversationalEnabled": false,
          "questionsAnsweringEnabled": false,
          "mindMapEnabled": true,
          "mindMapFormat": "plain",
          "pptExtractionEnabled": false,
          "autoChaptersEnabled": true,
          "autoChapterGranularity": "Coarse",
          "autoChapterTitleLengthLevel": "Short",
          "textPolishEnabled": false,
          "customPromptEnabled": true,
          "customPromptModel": "tingwu-turbo",
          "customPromptTransType": "chat",
          "customPromptContent": "Please help me extract the role corresponding to each speaker ID from the original text. Possible roles include sales staff and test drive customers. The original text is as follows: {Transcription}"
       }
    }
}'

End the real-time meeting and create minutes

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header 'Authorization: Bearer sk-******e181c' \
--header 'Content-Type: application/json' \
--data '{
    "model": "tingwu-meeting",
    "input": {
        "task": "createTask",
        "appId": "tw_***",
        "type": "realtime",
        "dataId": "BEc******syu"
    }
}'

​Prerequisites

​Overall call flow

​Endpoint

​Request method

​Request headers

​Request parameters

​Response parameters

​Request examples

​Create a real-time meeting

​End the real-time meeting and create minutes

Prerequisites

Overall call flow

Endpoint

Request method

Request headers

Request parameters

Response parameters

Request examples

Create a real-time meeting

End the real-time meeting and create minutes