Request API

API Description

Video stream moderation API. Submits a live or pre-recorded video stream URL (or RTC channel) and DeepCleer pulls the stream from the source, captures frames, extracts audio segments, and delivers per-frame and per-audio-segment results to the callback URLs you supply. Detects regulatory risks in both the visual track (political, pornography, violence & terrorism, QR codes, advertisements, image-text violations) and the audio track (political, pornography, advertising, prohibited, profanity, moaning, top-leader voiceprint, national anthem, prohibited songs), and can additionally identify business-scenario attributes such as gender, voice timbre, language, age, and minor presence.

Requirements

Item	Specification
Protocol	HTTP or HTTPS
Method	POST
Encoding	UTF-8
Format	All request and response parameters use JSON

Stream Requirements

Item	Specification
Standard stream URLs	RTMP, RTMPS, HLS, HTTP, HTTPS protocols; FLV, M3U8, and other common container formats
RTC providers	Agora, Tencent (TRTC), Zego, Volcano Engine, Alibaba Cloud — each with provider-specific parameters (see Stream Type)

Timeout Suggestion

Recommended timeout: 7 seconds for the submission call
Internal processing timeout: 3 seconds with one automatic retry; normal API response time is within 100 ms

ℹ️
The submission call only registers the stream for moderation — it returns almost immediately. Frame and audio results are delivered separately via the callback URLs you supply. Keep your callback handlers fast (< 2 seconds) so DeepCleer doesn't trigger unnecessary retries.

Callback Mechanism

Results are delivered to the imgCallback and audioCallback URLs you supply in the request. When DeepCleer calls your endpoint:

The request body is a JSON payload matching Stream Segment Callback Parameters.
Your endpoint must respond with HTTP 200 OK. Any non-200 response is treated as a delivery failure.
On failure, DeepCleer retries with the following intervals (in seconds): [5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60]. After 12 failed retries, the segment is dropped.
Your endpoint should be idempotent on requestId + imgUrl / audioUrl — the same segment may be delivered more than once if an earlier delivery succeeded but the response was lost in transit.

Stream Pull Retry Mechanism

To reduce failures caused by transient network issues, DeepCleer retries failed stream pulls as follows:

Standard streams and Zego / Tencent / Volcano streams: up to 12 retries. Each attempt lasts 5 minutes; intervals between attempts follow [5, 10, 15, 20, …, 60] seconds. For example, DeepCleer first attempts continuous stream pulling for 5 minutes; if unsuccessful, it waits 5 seconds and pulls again for another 5 minutes; if still unsuccessful, it waits 10 seconds and pulls again, and so on.
Agora streams: no retries. The connection is closed after a 5-minute stream pull timeout.

Request

Request URL

Cluster	Request URL
Singapore Video Stream Cluster	`http://api-videostream-xjp.fengkongcloud.com/videostream/v4`

Request Parameters

Parameter	Type	Required	Max Length	Description
`accessKey`	string	Yes	20	API authentication key. The default `accessKey` is sent in your onboarding email.
`appId`	string	Yes	64	Application identifier, such as `web` for your web application or `app` for your mobile app. The default `appId` is sent in your onboarding email. Contact DeepCleer if you need a new `appId`.
`eventId`	string	Yes	64	Event identifier used to distinguish moderation scenarios in your application, such as `liveStream` for live broadcasts or `rtcRoom` for RTC channels. The default `eventId` is sent in your onboarding email. Contact DeepCleer if you need a new `eventId`.
`imgType`	string	Conditional	1024	Image (frame) risk detection types. At least one of `imgType` or `imgBusinessType` must be provided. Multiple values can be combined with underscores, for example `POLITY_QRCODE_ADVERT`. See Image Detection Types.
`audioType`	string	Conditional	1024	Audio risk detection types. At least one of `audioType` or `audioBusinessType` must be provided when audio moderation is enabled. Multiple values can be combined with underscores, for example `POLITY_EROTIC`. Use `NONE` to skip audio moderation entirely. See Audio Detection Types.
`imgBusinessType`	string	Conditional	1024	Image business-label detection types. At least one of `imgType` or `imgBusinessType` must be provided. Multiple values can be combined with underscores. See Business Types of Visual Moderation.
`audioBusinessType`	string	Conditional	1024	Audio business-label detection types. At least one of `audioType` or `audioBusinessType` must be provided when audio moderation is enabled. Multiple values can be combined with underscores. See Audio Business Detection Types.
`imgCallback`	string	Yes	1024	Callback HTTP URL for captured-frame moderation results. DeepCleer posts image callback payloads to this endpoint.
`audioCallback`	string	Conditional	1024	Callback HTTP URL for audio-segment moderation results. Required when audio moderation is enabled. DeepCleer posts audio callback payloads to this endpoint.
`data`	object	Yes	1 MB	Request data content. Max 1 MB. See `data` Object.
`acceptLang`	string	No	-	Language for returned labels. Set `en` by default. Supported values: `en`, `zh`.

Image Detection Types

Combine multiple types with underscores, for example POLITY_QRCODE_ADVERT.

Value	Description
`POLITY`	Political content detection
`EROTIC`	Pornography and sexual content detection
`VIOLENT`	Violence, terrorism, and prohibited content detection
`QRCODE`	QR code detection
`ADVERT`	Advertisement detection
`IMGTEXTRISK`	Image-text violation detection (OCR)

Audio Detection Types

Combine multiple types with underscores, for example POLITY_EROTIC. Use NONE to skip audio moderation entirely.

Value	Description
`POLITY`	Political content detection
`EROTIC`	Pornographic content detection
`ADVERT`	Advertising detection
`BAN`	Prohibited content detection
`VIOLENT`	Violence and terrorism detection
`DIRTY`	Profanity or abusive language detection
`ADLAW`	Advertising law violation detection
`MOAN`	Moaning detection
`AUDIOPOLITICAL`	Top-leader voiceprint detection
`ANTHEN`	National anthem detection
`BANEDAUDIO`	Prohibited songs detection
`NONE`	Skip audio detection

Audio Business Detection Types

Combine multiple types with underscores. To detect timbre, singing, or language, GENDER must also be included.

Value	Description
`SING`	Singing detection
`LANGUAGE`	Language detection (Chinese, English, Cantonese, Tibetan, Uyghur, Korean, Mongolian, Other)
`MINOR`	Minor detection
`GENDER`	Gender detection
`TIMBRE`	Voice timbre detection
`VOICE`	Voice attributes
`AUDIOSCENE`	Audio scene detection
`AGE`	Age detection
`APPNAME`	App name detection

`data` Object

Parameter	Type	Required	Max Length	Description
`streamType`	string	Yes	-	Video stream source type. See Stream Type.
`tokenId`	string	Yes	64	Stable identifier for the end user, typically your internal user ID. Used for behavioral-risk signals such as spam, advertising, and repeat-offender detection. Alphanumeric with underscores and hyphens, up to 64 characters.
`anchorName`	string	No	-	Anchor display name. Usually used by human review workflows.
`audioDetectStep`	int32	No	-	Audio moderation step in 10-second segments. Integer range: `1`-`36`. `1` means skip one 10-second segment between moderated segments; `2` means skip two segments, and so on. Omit this field to moderate all audio segments.
`detectFrequency`	int32	No	-	Frame capture interval, in seconds. Range: `1`-`60`. Decimals are rounded down; values below `1` are treated as `1`. Default: `3` seconds.
`detectStep`	int32	No	-	Captured-frame moderation step. One captured frame is moderated per step. Must be `>= 1`. Omit this field to moderate all captured frames.
`deviceId`	string	No	128	Device-fingerprint identifier issued by the DeepCleer SDK. Used for user behavior analysis.
`gender`	string	No	-	End user's gender. Recommended values: `male`, `female`, `ambiguity`.
`imgBusinessDetectStep`	int32	No	-	Image business-label moderation step. One captured frame is moderated for `imgBusinessType` per step. Must be `>= 1`. Default: `1`, meaning all captured frames are checked for business labels.
`imgCompareBase`	string	No	1024	Reference image URL used for face comparison. Present when `imgBusinessType` includes `FACECOMPARE`. Supported formats: JPG, JPEG, PNG, WebP, GIF, TIFF, TIF, HEIF. Recommended minimum image size: 256 x 256 px. Animated images are not currently supported as reference images.
`ip`	string	No	64	Public IP address of the user. Accepts IPv4 or IPv6. Used for IP-based user behavior analysis.
`lang`	string	No	-	Language used for OCR and audio-text moderation. Pass `en` by default. For international traffic when the language is mixed, pass `auto` to enable automatic language detection. See Supported Languages.
`level`	int32	No	-	User level. Use this to configure different moderation policies for different user tiers. See User Levels.
`liveCover`	string	No	-	Livestream cover image. Usually used by human review workflows.
`liveTitle`	string	No	-	Livestream title. Usually used by human review workflows.
`receiveTokenId`	string	No	64	`tokenId` of the message recipient. Alphanumeric with underscores and hyphens, up to 64 characters.
`returnAllImg`	int32	No	-	Controls which frame moderation results are returned. `0` (default): return only non-`PASS` frame results. `1`: return all frame results.
`returnAllText`	int32	No	-	Controls which audio moderation results are returned. `0` (default): return only non-`PASS` audio segments and transcripts. `1`: return all audio segments and transcripts.
`returnFinishInfo`	int32	No	-	Whether to send a stream-end callback. `0` (default): do not send a stream-end callback. `1`: send a callback when stream moderation ends; callback payload includes `statCode`.
`returnPreAudio`	int32	No	-	Whether to return the previous audio segment. `0` (default): do not return previous audio. `1`: when the current segment is risky, `preAudioUrl` contains a 20-second clip covering the previous 10 seconds plus the current 10 seconds.
`returnPreText`	int32	No	-	Whether to return the previous audio transcript. `0` (default): do not return previous transcript. `1`: when the current segment is risky, `content` contains 20 seconds of transcript covering the previous 10 seconds plus the current 10 seconds.
`room`	string	No	64	Live-room or game-room ID. Can be used to apply room-level moderation policies.
`streamName`	string	No	64	Video stream name. Used for display in the DeepCleer console; recommended.
`url`	string	Conditional	600	Standard video stream URL to moderate. Required when `streamType` is `NORMAL`.
`agoraParam`	object	Conditional	-	Agora recording parameters. Required when `streamType` is `AGORA`. See `data.agoraParam` Object.
`trtcParam`	object	Conditional	-	Tencent TRTC recording parameters. Required when `streamType` is `TRTC`. See `data.trtcParam` Object.
`zegoParam`	object	Conditional	-	Zego recording parameters. Required when `streamType` is `ZEGO`. See `data.zegoParam` Object.
`volcParam`	object	Conditional	-	Volcano Engine recording parameters. Required when `streamType` is `VOLC`. See `data.volcParam` Object.
`aliParam`	object	Conditional	-	Alibaba Cloud recording parameters. Required when `streamType` is `ALI`. See `data.aliParam` Object.
`extra`	object	No	-	Auxiliary parameters. See `data.extra` Object.

Stream Type

Value	Description
`NORMAL`	Standard stream URL. Supported protocols: RTMP, RTMPS, HLS, HTTP, HTTPS. Provide the stream URL via `data.url`.
`AGORA`	Agora moderation. Provide recording parameters via `data.agoraParam`.
`TRTC`	Tencent TRTC moderation. Provide recording parameters via `data.trtcParam`.
`ZEGO`	Zego moderation. Provide recording parameters via `data.zegoParam`.
`VOLC`	Volcano Engine moderation. Provide recording parameters via `data.volcParam`.
`ALI`	Alibaba Cloud moderation. Provide recording parameters via `data.aliParam`.

When an RTC SDK recording solution is used, additional recording charges may be incurred by the RTC provider. Contact the relevant RTC provider for details.

User Levels

Value	Description
`0`	Lowest-level user, such as newly registered, completely inactive, or level-0 users
`1`	Lower-level user, such as low-activity or low-level users
`2`	Mid-level user, such as moderately active or mid-level users
`3`	Higher-level user, such as highly active or high-level users
`4`	Highest-level user, such as paying users or VIP users

Supported Languages

Value	Language
`en`	English
`zh`	Chinese
`ar`	Arabic
`hi`	Hindi
`es`	Spanish
`fr`	French
`ru`	Russian
`pt`	Portuguese
`id`	Indonesian
`de`	German
`ja`	Japanese
`tr`	Turkish
`vi`	Vietnamese
`it`	Italian
`th`	Thai
`tl`	Filipino
`ko`	Korean
`ms`	Malay
`auto`	Automatic language detection. Contact DeepCleer to enable.

`data.extra` Object

Parameter	Type	Required	Max Length	Description
`passThrough`	object	No	1024	Client pass-through field. DeepCleer does not process this field; it is echoed back in the callback payload as-is.

`data.agoraParam` Object

Required when streamType is AGORA.

Parameter	Type	Required	Max Length	Description
`appId`	string	Yes	64	Application identifier provided by Agora.
`channel`	string	Yes	64	Channel name provided by Agora.
`channelProfile`	int32	No	32	Agora recording channel mode. `0` (default): communication mode, such as 1-on-1 or group chats where any user can speak freely. `1`: live broadcast mode with host and audience roles.
`enableH265Support`	boolean	No	-	Whether to support H.265 video stream recording. `false` (default): do not support H.265, and remote users cannot send H.265 video. `true`: support H.265.
`enableIntraRequest`	boolean	No	-	Whether to enable keyframe requests. Default: `true`. This can improve audio and video experience under weak network conditions. To enable seeking in recordings made in individual-stream mode, set this to `false`. `false`: disable keyframe requests; all senders send keyframes every 2 seconds, and individual-stream recordings support seeking. `true`: sender controls keyframe requests, and individual-stream recordings do not support seeking.
`subscribeMode`	string	No	-	Subscription mode. `AUTO` (default): subscribe to all streams in the room. `UNTRUSTED`: pair with `untrustedUserIdList` to subscribe only to streams from users in the list; an empty list returns a parameter error. `TRUSTED`: pair with `trustedUserIdList` to subscribe only to streams from users not in the list. In `TRUSTED` mode, if no users outside the list join the room within a certain time, DeepCleer proactively ends moderation.
`token`	string	No	64	Authentication token. See Agora documentation for generation: https://docs.agora.io/cn/Recording/token_server?platform=CPP. Set the token validity period to exceed the channel duration to prevent stream-pull failures due to token expiration. Agora currently caps token validity at 24 hours; for channels lasting longer, set `returnFinishInfo` to `1`, watch for an end callback with `statCode` of `1` caused by an invalid or expired pull token, generate a new token, and resubmit the channel for moderation if it still requires moderation.
`uid`	int32	No	64	A 32-bit unsigned integer. When `token` is provided, supply the user ID used to generate the token. Must not collide with any actual user UID in the room; the recording-side UID must be unique.
`trustedUserIdList`	array	No	-	Trusted-user UID list. Effective when `subscribeMode` is `TRUSTED`. Must not be empty. DeepCleer will not subscribe to streams from users in this list. Comma-separated UID array, for example `[1, 2]`. Maximum: 17 users.
`untrustedUserIdList`	array	No	-	Untrusted-user UID list. Effective when `subscribeMode` is `UNTRUSTED`. Must not be empty. DeepCleer will only subscribe to streams from users in this list. Comma-separated UID array, for example `[1, 2]`. Maximum: 17 users.

`data.trtcParam` Object

Required when streamType is TRTC.

Parameter	Type	Required	Max Length	Description
`appScene`	int32	Yes	1	Application scene. `0` (default): video call. `1`: video live broadcast. See https://cloud.tencent.com/document/product/647/79634.
`demoSences`	int32	Yes	-	Recording type. `2`: individual stream recording. `4`: mixed stream recording. Note: the field name is `demoSences` on the wire and is preserved as a typo of "demoScenes"; flag for v5 cleanup.
`sdkAppId`	int32	Yes	64	The `sdkAppId` provided by Tencent.
`strRoomId`	string	Conditional	128	String room ID. Allowed characters: letters (`a-z`, `A-Z`), digits (`0-9`), underscores, and hyphens. One of `roomId` or `strRoomId` must be provided. If both are present, `roomId` takes priority.
`userId`	string	Yes	32	The `userId` assigned to the recording end. Allowed characters: letters (`a-z`, `A-Z`), digits (`0-9`), underscores, and hyphens.
`userSig`	string	Yes	128	Verification signature corresponding to the recording `userId`. Equivalent to a login password.
`roomId`	int32	Conditional	10	Numeric room ID. Range: `1`-`4294967294`. One of `roomId` or `strRoomId` must be provided. If both are present, `roomId` takes priority. Currently a maximum of 8 users per room can be moderated.

`data.zegoParam` Object

Required when streamType is ZEGO.

Parameter	Type	Required	Max Length	Description
`roomId`	string	Yes	64	Zego room ID.
`tokenId`	string	Yes	64	Authentication information provided by Zego. Used to obtain `identify_token` for login. See Zego documentation for generation: https://doc-zh.zego.im/article/15258. Note: `tokenId` is a unique identifier; a new token must be generated for each moderation request.

`data.volcParam` Object

Required when streamType is VOLC.

Parameter	Type	Required	Max Length	Description
`appId`	string	Yes	64	Application identifier provided by Volcano Engine.
`roomId`	string	Yes	128	Room ID.
`token`	string	Yes	64	Verification signature corresponding to the recording `userId`. Equivalent to a login password.
`userId`	string	Yes	32	The `userId` assigned to the recording end. Allowed characters: letters (`a-z`, `A-Z`), digits (`0-9`), underscores, and hyphens.

`data.aliParam` Object

Required when streamType is ALI.

Parameter	Type	Required	Max Length	Description
`room`	string	Yes	64	Room ID. Must exactly match the `channelID` used to generate the token. DeepCleer pulls and records streams on a per-room basis. `room` is a unique identifier; duplicate rooms will not result in duplicate stream pulls.
`token`	string	Yes	64	Token used by the pull-stream end to join the channel. See https://help.aliyun.com/zh/live/user-guide/token-based-authentication for generation. A new token must be generated for each moderation submission.
`userId`	int32	No	32	Alibaba user account identifier.

Synchronous Response

The synchronous response is an acknowledgement only. It confirms whether the stream was accepted for moderation. Frame and audio results are delivered later to the callback URLs you supplied. See Stream Segment Callback Parameters and, when returnFinishInfo is 1, Stream End Callback Parameters.

Response Parameters

Parameter	Type	Required	Description
`requestId`	string	Yes	Unique DeepCleer request identifier. Save this value to cancel moderation, correlate callbacks, and troubleshoot.
`code`	int32	Yes	Response code. See Response Codes.
`message`	string	Yes	Response message corresponding to the `code`.
`detail`	object	No	Additional response detail.
`dupRequestId`	string	No	Returned when `errorcode` is `1001`, indicating a duplicate stream request. Use this request ID to close moderation if the original response was missed.
`errorcode`	int32	No	Business error code. `1001`: duplicate stream request.

Response Codes

Code	Message
`1100`	Success
`1901`	QPS limit exceeded
`1902`	Invalid parameters
`1903`	Service failure
`1904`	Stream count limit exceeded
`9101`	Unauthorized operation

Stream Segment Callback Parameters

Per-segment results are delivered to imgCallback when contentType is 1 and to audioCallback when contentType is 2. Both callback payloads share the envelope below.

Note: Parameters other than code, message, and requestId are only guaranteed to be returned when code is 1100.

Parameter	Type	Required	Description
`requestId`	string	Yes	Unique DeepCleer request identifier, same as the value returned in the synchronous acknowledgement.
`code`	int32	Yes	Response code. See Response Codes.
`message`	string	Yes	Response message corresponding to the `code`.
`statCode`	int32	No	Callback status code. `0`: regular moderation result callback. `1`: stream-end result callback, only when `returnFinishInfo` is `1`.
`contentType`	int32	Yes	Distinguishes between image and audio callbacks. `1`: image (frame) callback. `2`: audio segment callback.
`frameDetail`	object	No	Frame moderation detail. Present when `contentType` is `1` and the frame has a risky label, or when `returnAllImg` is `1`. See `frameDetail` Object.
`audioDetail`	object	No	Audio segment moderation detail. Present when `contentType` is `2` and the segment has a risky label, or when `returnAllText` is `1`. See `audioDetail` Object.
`auxInfo`	object	No	Auxiliary information. Contains `passThrough` echoed from `data.extra.passThrough` in the original request.

`frameDetail` Object

Present when there are risky frames or when returnAllImg is 1.

Parameter	Type	Required	Description
`imgUrl`	string	Yes	URL of the captured frame.
`riskLevel`	string	Yes	Disposition recommendation. `PASS`: normal (allow). `REVIEW`: suspicious (route to manual review). `REJECT`: violation (block).
`riskLabel1`	string	Yes	Level 1 risk label. Returns `normal` when `riskLevel` is `PASS`.
`riskLabel2`	string	Yes	Level 2 risk label. Empty when `riskLevel` is `PASS`.
`riskLabel3`	string	Yes	Level 3 risk label. Empty when `riskLevel` is `PASS`.
`riskDescription`	string	Yes	Risk description. Returns `"Normal"` when `riskLevel` is `PASS`. Returns `"Hit custom list"` when a customer-defined list is matched. Otherwise format: `"Level 1: Level 2: Level 3"`. For reference only; do not use for programmatic logic.
`allLabels`	array	Yes	All risk labels matched on this frame. See `frameDetail.allLabels`.
`riskDetail`	object	No	Risk detail. See `frameDetail.riskDetail`.
`auxInfo`	object	Yes	Auxiliary information. See `frameDetail.auxInfo`.
`businessLabels`	array	No	Business labels matched on this frame. See `frameDetail.businessLabels`.

`frameDetail.allLabels`

Each element in the array:

Parameter	Type	Required	Description
`riskLevel`	string	No	Risk level: `PASS`, `REVIEW`, or `REJECT`.
`riskLabel1`	string	No	Level 1 risk label.
`riskLabel2`	string	No	Level 2 risk label.
`riskLabel3`	string	No	Level 3 risk label.
`riskDescription`	string	No	Risk description. Returns `"Normal"` when `riskLevel` is `PASS`. For reference only; do not use for programmatic logic.
`probability`	float	No	Confidence score from `0` to `1`. Higher values indicate greater confidence.

`frameDetail.riskDetail`

Parameter	Type	Required	Description
`riskSource`	int32	Yes	Risk source. `1000`: no risk. `1001`: text risk. `1002`: visual image risk.
`face_num`	int32	No	Number of faces detected.
`person_num`	int32	No	Number of persons detected.
`faces`	array	No	Names and positions of politically sensitive persons in the frame. Up to 10 entries, with the highest probability entries selected if more are detected. See Face Object.
`objects`	array	No	Detected objects or symbols with names and positions. See Object Info.
`ocrText`	object	No	OCR text content recognized in the frame. Present when `imgType` includes `IMGTEXTRISK` or `ADVERT`. Contains `text` (string): recognized text.
`matchedLists`	array	No	Matched custom list information. Returned only when a customer-defined list is hit. See Matched Lists.
`riskSegments`	array	No	High-risk content segments. Present when political, terrorism, prohibited, competitor, or advertising-law content is detected. See Risk Segments.
`persons`	array	No	Person names and positions in the frame. Up to 10 entries, with the highest probability entries selected. See Person Object.

Face Object

Parameter	Type	Required	Description
`id`	string	No	Identifier. The same person at the same position has the same ID across different labels. If the same person appears N times, N IDs are assigned.
`name`	string	No	Person name.
`face_ratio`	float	No	Face-to-frame ratio from `0` to `1`.
`probability`	float	No	Confidence score from `0` to `1`.
`location`	array	No	Face position coordinates `[x1, y1, x2, y2]` representing top-left and bottom-right corners. Example: `[207, 522, 340, 567]`.

Object Info

Parameter	Type	Required	Description
`id`	string	No	Object or symbol identifier. The same object at the same position has the same ID across different labels.
`name`	string	No	Object name.
`probability`	float	No	Confidence score from `0` to `1`.
`qrContent`	string	No	QR code URL detected in the frame.
`location`	array	No	Object position coordinates `[x1, y1, x2, y2]`. Example: `[207, 522, 340, 567]`.

Matched Lists

Parameter	Type	Required	Description
`name`	string	No	Name of the matched list.
`words`	array	No	Sensitive word details.
`words[].word`	string	No	The matched sensitive word.
`words[].position`	array	No	Position of the sensitive word.

Risk Segments

Parameter	Type	Required	Description
`segment`	string	No	High-risk content segment text.
`position`	array	No	Position of the segment, 0-indexed.

Person Object

Parameter	Type	Required	Description
`id`	string	No	Identifier. The same person has the same ID across different labels.
`person_ratio`	float	No	Person-to-frame ratio from `0` to `1`.
`probability`	float	No	Confidence score from `0` to `1`.
`location`	array	No	Person position coordinates.

`frameDetail.auxInfo`

Parameter	Type	Required	Description
`beginProcessTime`	int64	Yes	Processing start time. 13-digit Unix timestamp in milliseconds (UTC).
`finishProcessTime`	int64	Yes	Processing end time. 13-digit Unix timestamp in milliseconds (UTC).
`detectType`	int32	No	Whether the captured frame was actually moderated. Only returned when the `detectStep` request parameter is set. `1`: the frame was moderated. `2`: the frame was skipped according to `detectStep`.
`imgTime`	string	No	Time the frame was captured, as the absolute time of the frame in the video stream.
`room`	string	No	Room ID.
`similarityDedup`	int32	No	Auxiliary parameter. Only returned when the similar-frame deduplication feature changed the outer `riskLevel` from `REJECT` or `REVIEW` to `PASS`. `1`: similar-frame deduplication is active.
`strUserId`	string	No	User identifier for distinguishing violating users within a room. Unrelated to the `userId` request parameter; this is the individual stream user ID. Returned for ZEGO room-level moderation, TRTC individual-stream moderation, VOLC, and ALI.
`userId`	int32	No	Agora user account identifier. Only present in individual-stream Agora scenarios. The returned `userId` is the actual user ID in the room, unrelated to the `uid` request parameter.

`frameDetail.businessLabels`

Each element in the array:

Parameter	Type	Required	Description
`businessLabel1`	string	Yes	Level 1 business label.
`businessLabel2`	string	Yes	Level 2 business label.
`businessLabel3`	string	Yes	Level 3 business label.
`businessDescription`	string	Yes	Business label description. Format: `"Level 1: Level 2: Level 3"`.
`probability`	float	Yes	Confidence score from `0` to `1`. Higher values indicate greater confidence.
`confidenceLevel`	int32	No	Confidence level from `0` to `2`. Higher values indicate greater confidence.
`businessDetail`	object	No	Business label details. May contain `face_num`, `person_num`, `faces`, `objects`, and `persons` with the same structure as `frameDetail.riskDetail`.

`audioDetail` Object

Present when there are risky audio segments or when returnAllText is 1.

Parameter	Type	Required	Description
`audioUrl`	string	Yes	URL of the audio segment.
`riskLevel`	string	Yes	Disposition recommendation. `PASS`: normal (allow). `REVIEW`: suspicious (route to manual review). `REJECT`: violation (block).
`riskLabel1`	string	Yes	Level 1 risk label. Returns `normal` when `riskLevel` is `PASS`.
`riskLabel2`	string	Yes	Level 2 risk label. Empty when `riskLevel` is `PASS`.
`riskLabel3`	string	Yes	Level 3 risk label. Empty when `riskLevel` is `PASS`.
`riskDescription`	string	Yes	Risk description. Returns `"Normal"` when `riskLevel` is `PASS`. Returns `"Hit custom list"` when a customer-defined list is matched. Otherwise format: `"Level 1: Level 2: Level 3"`. For reference only; do not use for programmatic logic.
`vadCode`	int32	Yes	Voice activity flag. `0`: silent segment. `1`: non-silent segment.
`allLabels`	array	Yes	All risk labels matched on this segment. See `audioDetail.allLabels`.
`riskDetail`	object	No	Risk detail per segment. See `audioDetail.riskDetail`.
`content`	string	No	Audio-to-text transcription for this segment. When `returnPreText` is `1` and the current segment is `REJECT`, returns 20 seconds of transcript covering the previous 10 seconds plus the current 10 seconds. Otherwise returns only the current segment transcript.
`preAudioUrl`	string	No	Previous audio segment URL. When `returnPreAudio` is `1` and the current segment is `REJECT`, returns a 20-second audio clip covering the previous 10 seconds plus the current 10 seconds. Otherwise not returned.
`auxInfo`	object	No	Auxiliary information. See `audioDetail.auxInfo`.
`businessLabels`	array	No	Business labels matched on this segment. See `audioDetail.businessLabels`.

`audioDetail.allLabels`

Each element in the array:

Parameter	Type	Required	Description
`riskLevel`	string	Yes	Risk level: `PASS`, `REVIEW`, or `REJECT`.
`riskLabel1`	string	Yes	Level 1 risk label. Returns `normal` when `riskLevel` is `PASS`.
`riskLabel2`	string	Yes	Level 2 risk label. Empty when `riskLevel` is `PASS`.
`riskLabel3`	string	Yes	Level 3 risk label. Empty when `riskLevel` is `PASS`.
`riskDescription`	string	Yes	Risk description. Returns `"Normal"` when `riskLevel` is `PASS`. Returns `"Hit custom list"` when a customer-defined list is matched. Otherwise format: `"Level 1: Level 2: Level 3"`. For reference only; do not use for programmatic logic.

`audioDetail.riskDetail`

Parameter	Type	Required	Description
`riskSource`	int32	Yes	Risk source. `1000`: no risk. `1001`: text risk. `1002`: visual image risk. `1003`: audio voice risk.
`audioText`	string	No	Audio-to-text transcription for this segment.
`matchedLists`	array	No	Matched custom list information. Returned only when a customer-defined list is hit. Same structure as Matched Lists.
`riskSegments`	array	No	High-risk content segments. Present when political, terrorism, prohibited, competitor, or advertising-law content is detected. Same structure as Risk Segments.

`audioDetail.auxInfo`

Parameter	Type	Required	Description
`audioStartTime`	string	Yes	Violation content start time, as absolute time.
`audioEndTime`	string	Yes	Violation content end time, as absolute time.
`beginProcessTime`	int64	Yes	Processing start time. 13-digit Unix timestamp in milliseconds (UTC).
`finishProcessTime`	int64	Yes	Processing end time. 13-digit Unix timestamp in milliseconds (UTC).
`room`	string	No	Room ID.
`strUserId`	string	No	User identifier for distinguishing violating users within a room. Unrelated to the `userId` request parameter; this is the individual stream user ID. Returned for ZEGO room-level moderation, TRTC individual-stream moderation, VOLC, and ALI.
`userId`	int32	No	Agora user account identifier. Only present in individual-stream Agora scenarios. The returned `userId` is the actual user ID in the room, unrelated to the `uid` request parameter.

Note on field casing: audioStartTime and audioEndTime use uppercase T, while the standalone Audio Moderation APIs use lowercase t (audioStarttime / audioEndtime). Preserved exactly as returned on the wire; flag for v5 cleanup.

`audioDetail.businessLabels`

Each element in the array:

Parameter	Type	Required	Description
`businessLabel1`	string	Yes	Level 1 business label.
`businessLabel2`	string	Yes	Level 2 business label.
`businessLabel3`	string	Yes	Level 3 business label.
`businessDescription`	string	Yes	Business label description. Format: `"Level 1: Level 2: Level 3"`.
`probability`	float	Yes	Confidence score from `0` to `1`. Higher values indicate greater confidence.
`confidenceLevel`	int32	No	Confidence level from `0` to `2`. Higher values indicate greater confidence.
`riskDetail`	object	No	Business risk detail. Fields: `riskSource` (int32; `1000`, `1001`, or `1003`), `audioText` (string), `matchedLists` (array, same as above), and `riskSegments` (array, same as above).

`tokenProfileLabels` - Account Attribute Labels

Returned only when tokenId is provided and the labeling service is enabled. Each element in the array:

Parameter	Type	Required	Description
`label1`	string	No	Level 1 label.
`label2`	string	No	Level 2 label.
`label3`	string	No	Level 3 label.
`description`	string	No	Label description. For reference only; do not use for programmatic logic.
`timestamp`	int64	No	Label timestamp. 13-digit Unix timestamp in milliseconds (UTC).

`tokenRiskLabels` - Account Risk Labels

Returned only when tokenId is provided and the labeling service is enabled. Each element in the array:

Parameter	Type	Required	Description
`label1`	string	No	Level 1 label.
`label2`	string	No	Level 2 label.
`label3`	string	No	Level 3 label.
`description`	string	No	Label description. For reference only; do not use for programmatic logic.
`timestamp`	int64	No	Label timestamp. 13-digit Unix timestamp in milliseconds (UTC).

Stream End Callback Parameters

Delivered when returnFinishInfo is 1 and moderation of the stream completes, either naturally, via stream-pull failure, or via the close-moderation API.

Parameter	Type	Required	Description
`requestId`	string	Yes	Unique DeepCleer request identifier, same as the value returned in the synchronous acknowledgement.
`code`	int32	Yes	Response code. See Response Codes.
`message`	string	Yes	Response message corresponding to the `code`.
`riskLevel`	string	Yes	Overall stream disposition recommendation. `PASS`: normal (allow). `REVIEW`: suspicious (route to manual review). `REJECT`: violation (block).
`statCode`	int32	Yes	Callback status code. `0`: regular moderation result callback. `1`: stream-end result callback. Always `1` for this payload.
`contentType`	int32	Yes	Distinguishes between image and audio end callbacks. `1`: image moderation end callback. `2`: audio moderation end callback.
`pullStreamSuccess`	boolean	Yes	Whether the stream pull succeeded. `true`: stream pull succeeded. `false`: stream pull failed, meaning not even a single frame was successfully captured.
`auxInfo`	object	Yes	Auxiliary information. See Stream End `auxInfo`.
`requestParams`	object	No	Echo of all fields submitted under `data` in the original request. Returned when `contentType` is `2`.
`detail`	object	No	Detail information. Returned when `contentType` is `1`. Contains `requestParams` (object): echo of all fields submitted under `data` in the original request.

Stream End `auxInfo`

Parameter	Type	Required	Description
`streamTime`	int32	Yes	Total stream moderation duration. Returned in the final callback after the stream ends. When interval moderation (`audioDetectStep`) is applied, this may differ from the actual stream duration.

Example

Request Example

{
  "accessKey": "*********",
  "appId": "defaulttest",
  "audioBusinessType": "SING_LANGUAGE",
  "audioCallback": "http://www.xxx.top/callbackxxx",
  "audioType": "POLITY_EROTIC_ADVERT_MOAN",
  "data": {
    "detectFrequency": 10,
    "detectStep": 1,
    "extra": {
      "passThrough": {
        "passThrough1": "111",
        "passThrough2": "222",
        "passThrough3": "333"
      }
    },
    "ip": "123.171.34.4",
    "lang": "zh",
    "returnAllImg": 1,
    "returnAllText": 1,
    "returnPreAudio": 1,
    "returnPreText": 1,
    "room": "5e1854a6a0a79d0001a09bc3",
    "streamType": "NORMAL",
    "tokenId": "123",
    "url": "http://rtmp.xxxx.cn/live/3637778raLSXdOdu.flv"
  },
  "eventId": "VIDEOSTREAM",
  "imgBusinessType": "BODY_FOOD_3CPRODUCTSLOGO",
  "imgCallback": "http://www.xxx.top/callbackxxx",
  "imgType": "POLITY_EROTIC_ADVERT"
}

Response Example

{
  "code": 1100,
  "message": "Success",
  "requestId": "66fb85e3149bb9e13d6c72161cc6c6cf"
}

Frame Capture Callback Example

{
  "auxInfo": {
    "passThrough": {
      "passThrough1": "111",
      "passThrough2": "222",
      "passThrough3": "333"
    }
  },
  "code": 1100,
  "contentType": 1,
  "frameDetail": {
    "allLabels": [
      {
        "riskDescription": "Involvement in politics: Involvement in politics: Involvement in politics",
        "riskLabel1": "politics",
        "riskLabel2": "shezheng",
        "riskLabel3": "shezheng",
        "riskLevel": "REJECT"
      }
    ],
    "auxInfo": {
      "beginProcessTime": 1639825248361,
      "detectType": 1,
      "finishProcessTime": 1639825248809,
      "imgTime": "2021-12-18 19:00:48.375",
      "room": "5e1854a6a0a79d0001a09bc3"
    },
    "businessLabels": [],
    "imgUrl": "http://bj.cos.ap-beijing.xxx.com/image/1639825145166_vs130_1639825248361471656.jpg",
    "riskDescription": "Involvement in politics: Involvement in politics: Involvement in politics",
    "riskDetail": {
      "ocrText": {
        "text": "Page 4 (ban) Page 5 (violence)"
      },
      "riskSource": 1002
    },
    "riskLabel1": "politics",
    "riskLabel2": "shezheng",
    "riskLabel3": "shezheng",
    "riskLevel": "REJECT"
  },
  "message": "Success",
  "requestId": "1639825145166_vs130_1639825248361471656"
}

Stream End Callback Example

{
  "auxInfo": {
    "streamTime": 70
  },
  "code": 1100,
  "contentType": 1,
  "detail": {
    "requestParams": {
      "detectFrequency": 10,
      "detectStep": 1,
      "extra": {
        "passThrough": {
          "passThrough1": "111",
          "passThrough2": "222",
          "passThrough3": "333"
        }
      },
      "ip": "123.171.34.4",
      "lang": "zh",
      "returnAllImg": 1,
      "returnAllText": 1,
      "returnPreAudio": 1,
      "returnPreText": 1,
      "room": "5e1854a6a0a79d0001a09bc3",
      "streamType": "NORMAL",
      "tokenId": "123",
      "url": "http://rtmp.example.com/live/3637778raLSXdOdu.flv"
    }
  },
  "message": "Success",
  "pullStreamSuccess": true,
  "requestId": "5515ce1f9b474a6c4a3d79a8dfcaeaf4",
  "riskLevel": "PASS",
  "statCode": 1
}

API Description

Requirements

Stream Requirements

Timeout Suggestion

Callback Mechanism

Stream Pull Retry Mechanism

Request

Request URL

Request Parameters

Image Detection Types

Audio Detection Types

Audio Business Detection Types

data Object

Stream Type

User Levels

Supported Languages

data.extra Object

data.agoraParam Object

data.trtcParam Object

data.zegoParam Object

data.volcParam Object

data.aliParam Object

Synchronous Response

Response Parameters

Response Codes

Stream Segment Callback Parameters

frameDetail Object

frameDetail.allLabels

frameDetail.riskDetail

Face Object

Object Info

Matched Lists

Risk Segments

Person Object

frameDetail.auxInfo

frameDetail.businessLabels

audioDetail Object

audioDetail.allLabels

audioDetail.riskDetail

audioDetail.auxInfo

audioDetail.businessLabels

tokenProfileLabels - Account Attribute Labels

tokenRiskLabels - Account Risk Labels

Stream End Callback Parameters

Stream End auxInfo

Example

Request Example

Response Example

Frame Capture Callback Example

Stream End Callback Example

`data` Object

`data.extra` Object

`data.agoraParam` Object

`data.trtcParam` Object

`data.zegoParam` Object

`data.volcParam` Object

`data.aliParam` Object

`frameDetail` Object

`frameDetail.allLabels`

`frameDetail.riskDetail`

`frameDetail.auxInfo`

`frameDetail.businessLabels`

`audioDetail` Object

`audioDetail.allLabels`

`audioDetail.riskDetail`

`audioDetail.auxInfo`

`audioDetail.businessLabels`

`tokenProfileLabels` - Account Attribute Labels

`tokenRiskLabels` - Account Risk Labels

Stream End `auxInfo`