Create Real-Time ASR Subtitle Tasks for Live Streams - ApsaraVideo Live

Creates a live subtitle task to transcribe an audio stream to text in real time.

Operation description

This API is currently under maintenance. We recommend using a smart workflow to implement this feature. For more information, see Configure a smart workflow.

QPS limit

The QPS (queries per second) limit for this API is 20 for each user. API calls that exceed this limit are throttled, which may disrupt your service. Call this API at a reasonable rate to prevent service disruptions.

Try it now

Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

Test

RAM authorization

The table below describes the authorization required to call this API. You can define it in a Resource Access Management (RAM) policy. The table's columns are detailed below:

Action: The actions can be used in the Action element of RAM permission policy statements to grant permissions to perform the operation.
API: The API that you can call to perform the action.
Access level: The predefined level of access granted for each API. Valid values: create, list, get, update, and delete.
Resource type: The type of the resource that supports authorization to perform the action. It indicates if the action supports resource-level permission. The specified resource must be compatible with the action. Otherwise, the policy will be ineffective.
- For APIs with resource-level permissions, required resource types are marked with an asterisk (*). Specify the corresponding Alibaba Cloud Resource Name (ARN) in the Resource element of the policy.
- For APIs without resource-level permissions, it is shown as All Resources. Use an asterisk (*) in the Resource element of the policy.
Condition key: The condition keys defined by the service. The key allows for granular control, applying to either actions alone or actions associated with specific resources. In addition to service-specific condition keys, Alibaba Cloud provides a set of common condition keys applicable across all RAM-supported services.
Dependent action: The dependent actions required to run the action. To complete the action, the RAM user or the RAM role must have the permissions to perform all dependent actions.

Action

Access level

Resource type

Condition key

Dependent action

live:CreateRtcAsrTask

create

*Domain

acs:live:*:{#accountId}:domain/{#DomainName}

None

Request parameters

Parameter	Type	Required	Description	Example
RegionId	string	No	The ID of the region.	cn-shanghai
Mode	string	Yes	The stream type. Valid values: `live` and `rtc`. The value `live` indicates a standard live stream, such as a stream ingested over Real-Time Messaging Protocol (RTMP).	live
SDKAppID	string	No	The ARTC application ID. Note This parameter is required and takes effect only when `Mode` is set to `rtc`.	appId
ChannelID	string	No	The channel ID. Note This parameter is required and takes effect only when `Mode` is set to `rtc`.	channelId
RtcUserId	string	No	The ID of the user publishing the audio stream. Note This parameter is required and takes effect only when `Mode` is set to `rtc`. You can specify only one user ID.	user1
StreamURL	string	No	The streaming URL. Note This parameter is required and takes effect only when `Mode` is set to `live`.	rtmp://xxx
Language	string	Yes	The source language of the audio stream. Valid values: `ja`: Japanese `yue`: Cantonese `fspk`: Mixed Mandarin and English `en`: English `cn`: Mandarin	cn
CallbackURL	string	Yes	The URL to receive transcription results.	http://xxx.com
AuthKey	string	No	The key for generating the callback MD5 signature. Note During callbacks, two headers are added to the request for authentication: `SIG-TIME`, which is the current timestamp, and `ASR-SIG`, which is the MD5 signature. The `ASR-SIG` is calculated as follows: md5(${SIG-TIME}/${CallbackURL}/${AuthKey})	abcd
TranslateEnabled	boolean	No	Specifies whether to enable translation.	true
TargetLanguages	string	No	The target language for translation. Valid values: `cn`: Chinese `en`: English `ja`: Japanese	en
AutoTerminateEnabled	boolean	No	Specifies whether to automatically terminate the task if a stream interruption exceeds the `AutoTerminateDelay`. Default value: `false`.	true
AutoTerminateDelay	integer	No	The maximum duration of a stream interruption, in seconds, before the task is automatically terminated. This parameter applies only when `AutoTerminateEnabled` is set to `true`. Range: 1 to 10.	5
ReportInterval	integer	No	The interval for sending transcription results to your callback URL. Unit: milliseconds. Range: -1 to 500. -1: Sends callbacks only for the final transcription of a complete sentence. No intermediate results are sent. 0 or not specified: Sends callbacks in real time as transcription results are generated. A value from 1 to 500: Sends callbacks periodically at the specified interval.	5

Sample callback

The service POSTs transcription results as a JSON request body to your callback URL. For details about the Content parameter and the callback process, see Interaction flow and implementation. The following is an example of a callback payload:

{
    "task_id": "asr-cf8c70d7-3b8d-496c-98f8-4785******",
    "sdk_app_id": "",
    "channel_id": "",
    "rtc_user_id": "",
    "callback_time_stamp": 1723433155645,
    "language": "cn",
    "content": "{\"header\":{\"nls_task_id\":\"af95c5cc332549f689f3153bc9******\",\"task_key\":\"tl_2977564_17234*****\",\"namespace\":\"SpeechTranscriber\",\"name\":\"TranscriptionResultChanged\",\"task_id\":\"413937911b874146b5796******\",\"message_id\":\"abfc9e9994e748a38499e1******\",\"status_text\":\"Success.\",\"status\":20000000},\"payload\":{\"result\":\"Meeting with you all here\",\"confidence\":0.0,\"words\":[{\"startTime\":0,\"text\":\"Meeting\",\"endTime\":510},{\"startTime\":510,\"text\":\"with\",\"endTime\":1020},{\"startTime\":1020,\"text\":\"you all\",\"endTime\":1530},{\"startTime\":1530,\"text\":\"here\",\"endTime\":2040}],\"index\":0,\"time\":2040,\"fixed_result\":\"\",\"unfixed_result\":\"\",\"status\":0}}"
  }

Response elements

Element	Type	Description	Example
	object
Description	string	`success` if the request is successful; otherwise, an error message.	success
RequestId	string	The request ID.	7FF5417D-06E9-5A2C-9A70-581F6149E6C1
RetCode	integer	`2000` if the request is successful; other values indicate a failure.	2000
TaskId	string	The task ID.	asr-a6ac15e0-9118-4b4c-9e64-306163a0****

Examples

Success response

JSON format

{
  "Description": "success",
  "RequestId": "7FF5417D-06E9-5A2C-9A70-581F6149E6C1",
  "RetCode": 2000,
  "TaskId": "asr-a6ac15e0-9118-4b4c-9e64-306163a0****"
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.