Sync API

Detect regulatory risks in audio content including political content, pornography, advertising, and violence & terrorism. Combine with your business scenarios to identify minors, voice timbre, and other content.

API Description

Synchronous detection API that returns recognition results directly. Recommended to use the HTTP protocol for API calls.

Audio Requirements

Item	Specification
Audio types	URL, BASE64
Supported formats	WAV, MP3, AAC, AMR, 3GP, M4A, WMA, OGG, APE, FLAC, ALAC, WAVPACK, SILK_V3, etc.
Duration limit	≤ 60 seconds
Size limit	≤ 18 MB

ℹ️
Audio URLs should be downloaded from a CDN origin server. The origin server must not be a single point of failure, otherwise audio download failures may prevent moderation.

Timeout

Synchronous request: recommended timeout of 10 seconds
Async request: recommended timeout of 5 seconds
Response time depends on audio download time. Ensure the storage service hosting the audio is stable and reliable. Actual duration varies based on the request type and audio size.

Request

Request URL

Cluster	Request URL	Supported Products
Shanghai	`http://api-audio-sh.fengkongcloud.com/audiomessage/v4`	Chinese
Singapore	`http://api-audio-xjp.fengkongcloud.com/audiomessage/v4`	Chinese

Request Parameters

Parameter	Type	Required	Description
`accessKey`	string	Yes	Company key, provided by ISHUMEI. See the onboarding email for details.
`appId`	string	Yes	Application identifier. Contact ISHUMEI to activate. Use the value provided by ISHUMEI. Default value is in the onboarding email.
`eventId`	string	Yes	Event identifier. Contact ISHUMEI to activate. Use the value provided by ISHUMEI. Default value is in the onboarding email.
`type`	string	No	Risk detection types. Either `type` or `businessType` is required. See Risk Detection Types.
`businessType`	string	No	Business label detection types. Either `type` or `businessType` is required. See Business Detection Types.
`contentType`	string	Yes	Format of the audio content. `URL`: audio URL address. `RAW`: base64-encoded audio data.
`content`	string	Yes	Audio content — either a URL address or base64-encoded data. Base64 data limit: 15 MB. Only PCM, WAV, and MP3 formats are supported for base64. PCM format must use 16-bit little-endian encoding. PCM and WAV formats are recommended.
`btId`	string	Yes	Unique audio file identifier for matching callback results. Max 128 characters (truncated if exceeded). Must not be duplicated.
`data`	object	Yes	Request data content. Max 1 MB. See `data` Object.

Risk Detection Types

Combine multiple types with underscores (e.g., POLITY_EROTIC_MOAN). Recommended: POLITY_EROTIC_MOAN_ADVERT.

Value	Description
`AUDIOPOLITICAL`	Top leader voiceprint detection
`POLITY`	Political content detection
`EROTIC`	Pornographic content detection
`ADVERT`	Advertising detection
`BAN`	Prohibited content detection
`VIOLENT`	Violence & terrorism detection
`ANTHEN`	National anthem detection
`MOAN`	Moaning detection
`DIRTY`	Abusive language detection
`BANEDAUDIO`	Prohibited songs detection
`COPYRIGHTSONGS`	Copyrighted songs detection

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
`GENDER`	Gender detection
`TIMBRE`	Voice timbre detection
`VOICE`	Voice attributes
`MINOR`	Minor detection
`AUDIOSCENE`	Audio scene detection
`AGE`	Age detection

`data` Object

Parameter	Type	Required	Description
`tokenId`	string	No	User account identifier for behavior analysis. Recommended to pass the user UID.
`receiveTokenId`	string	No	Message receiver's `tokenId` for private chat scenarios. Alphanumeric with underscores and hyphens, up to 64 characters.
`deviceId`	string	No	ISHUMEI device fingerprint identifier. Unique device ID generated by the ISHUMEI SDK.
`ip`	string	No	IPv4 or IPv6 address of the user who sent the audio.
`dataId`	string	No	Custom data identifier.
`level`	int	No	User level for configuring different interception strategies. See User Levels.
`gender`	string	No	User gender. `male` or `female`.
`formatInfo`	string	No	Audio data format. Required when `contentType` is `RAW`. Values: `pcm`, `wav`, `mp3`.
`rate`	int	No	Audio sample rate. Required when format is `pcm`. Range: 8000–32000.
`track`	int	No	Audio channels. Required when format is `pcm`. `1`: mono. `2`: stereo.
`returnAllText`	int	No	Controls which audio segments are returned. `0` (default): return only risk segments (`REVIEW` and `REJECT`). `1`: return all segments (including `PASS`). This only controls segment-level results in `audioDetail`; it does not affect the overall result.

User Levels

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

Response

Response Parameters

ℹ️
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 request identifier.
`code`	int	Yes	Response code. See Response Codes.
`message`	string	Yes	Response message corresponding to the `code`.
`detail`	json	No	Detailed response data. Required when `code` is `1100`. See `detail` Object.

Response Codes

Code	Description
`1100`	Success
`1101`	Processing
`1901`	QPS limit exceeded
`1902`	Invalid parameters
`1903`	Service failure
`1904`	Download failure
`1905`	Decoding failure
`9100`	Insufficient balance
`9101`	Unauthorized operation

`detail` Object

Parameter	Type	Required	Description
`riskLevel`	string	Yes	Overall disposition recommendation. `PASS`, `REVIEW`, or `REJECT`. During initial integration, it is recommended not to use results directly for blocking — adjust interception thresholds first to match expectations.
`audioText`	string	Yes	Full audio-to-text transcription result.
`audioTime`	int	Yes	Total audio duration in seconds.
`audioDetail`	json_array	Yes	Audio segment information. See `audioDetail` Array.
`audioTags`	json_object	No	Audio tags including gender, timbre, and singing detection. Legacy compatibility field — use `businessLabels` instead. See `audioTags` Object.

`audioDetail` Array

Each element represents an audio segment:

Parameter	Type	Required	Description
`requestId`	string	Yes	Unique identifier for this audio segment.
`audioStarttime`	float	Yes	Segment start time relative to the audio beginning, in seconds.
`audioEndtime`	float	Yes	Segment end time relative to the audio beginning, in seconds.
`audioUrl`	string	Yes	Audio segment URL (MP3 format).
`riskLevel`	string	Yes	Segment risk level. `PASS`, `REVIEW`, or `REJECT`.
`riskLabel1`	string	Yes	Level 1 risk label.
`riskLabel2`	string	Yes	Level 2 risk label.
`riskLabel3`	string	Yes	Level 3 risk label.
`riskDescription`	string	Yes	Risk description. For reference only — do not use for programmatic logic.
`riskDetail`	json_object	No	Risk detail information. See Segment `riskDetail`.
`allLabels`	json_array	No	All risk labels. See Segment `allLabels`.
`businessLabels`	json_array	No	All business labels. See Segment `businessLabels`.

Segment `allLabels`

Each element in the allLabels array:

Parameter	Type	Required	Description
`riskLabel1`	string	Yes	Level 1 risk label.
`riskLabel2`	string	Yes	Level 2 risk label.
`riskLabel3`	string	Yes	Level 3 risk label.
`riskDescription`	string	Yes	Risk description. For reference only — do not use for programmatic logic.
`riskLevel`	string	Yes	Risk level: `PASS`, `REVIEW`, or `REJECT`.
`probability`	float	No	Confidence score (0–1). Higher values indicate higher risk probability.
`riskDetail`	json_object	No	Risk detail information. See Segment `riskDetail`.

Segment `riskDetail`

Parameter	Type	Required	Description
`audioText`	string	No	Audio-to-text transcription result for this segment.
`riskSource`	int	No	Risk source: `1000` (no risk), `1001` (text risk), `1003` (audio risk).
`matchedLists`	json_array	No	Matched custom list information. Returned only when a custom list is hit.
`matchedLists[].name`	string	Yes	Name of the custom list.
`matchedLists[].words`	json_array	Yes	Sensitive word information from the matched list.
`matchedLists[].words[].word`	string	Yes	The matched sensitive word.
`matchedLists[].words[].position`	int_array	Yes	Position of the sensitive word.
`riskSegments`	json_array	No	High-risk content segments.
`riskSegments[].segment`	string	No	High-risk content segment text.
`riskSegments[].position`	int_array	No	Position of the high-risk segment.

Segment `businessLabels`

Each element in the businessLabels 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".
`confidenceLevel`	int	No	Confidence level (0–2). Higher values indicate greater confidence.
`probability`	float	No	Confidence score (0–1).
`businessDetail`	json_object	No	Detailed information. Reserved field.

`audioTags` Object

⚠️
This is a legacy compatibility field. Use businessLabels in audioDetail instead for new integrations.

Parameter	Type	Required	Description
`gender`	object	No	Gender detection result.
`gender.label`	string	Yes	Gender label name (e.g., "Male", "Female").
`gender.probability`	int	No	Gender probability (0–100). Higher values indicate greater likelihood.
`timbre`	array	No	Voice timbre detection results. Each element contains `label` and `probability`. Possible label values: Uncle, Young Man, Boy, Elderly Man, Queen, Mature Woman, Young Woman, Loli, Middle-aged Woman, Male, Female, No Voice.
`language`	array	No	Language detection results. Each element contains `label` and `confidence`.

Language Labels

Label	Description
`0`	Mandarin Chinese
`1`	English
`2`	Cantonese
`3`	Tibetan
`4`	Uyghur
`5`	Mongolian
`6`	Korean
`-1`	Other languages

Examples

Request Example

{
  "accessKey": "YOUR_ACCESS_KEY",
  "appId": "default",
  "eventId": "default",
  "type": "POLITY_EROTIC",
  "businessType": "TIMBRE",
  "btId": "test1",
  "contentType": "URL",
  "content": "https://example.com/audio/sample.mp3",
  "data": {
    "returnAllText": 1,
    "tokenId": "token-short"
  }
}

Response Example

{
  "code": 1100,
  "message": "Success",
  "requestId": "817c8509359500c898a762ffe93a582b",
  "btId": "1667392054643",
  "detail": {
    "audioDetail": [
      {
        "requestId": "817c8509359500c898a762ffe93a582b_a0000",
        "audioStarttime": 0,
        "audioEndtime": 10,
        "audioUrl": "http://example.com/audio_segment_a0000.mp3",
        "businessLabels": [
          {
            "businessDescription": "Singing: Singing: Singing",
            "businessDetail": {},
            "businessLabel1": "sing",
            "businessLabel2": "changge",
            "businessLabel3": "changge",
            "confidenceLevel": 2,
            "probability": 0.858334402569294
          }
        ],
        "allLabels": [],
        "riskLevel": "REJECT",
        "riskLabel1": "abuse",
        "riskLabel2": "buwenmingyongyu",
        "riskLabel3": "qingdubuwenmingyongyu",
        "riskDescription": "Abuse: Uncivilized language: Mild uncivilized language",
        "riskDetail": {
          "audioText": "Recognized audio text content..."
        }
      }
    ],
    "audioTags": {
      "gender": {
        "label": "Female",
        "probability": 95
      },
      "language": [
        {
          "confidence": 0,
          "label": 2
        },
        {
          "confidence": 99,
          "label": 0
        },
        {
          "confidence": 0,
          "label": 1
        }
      ],
      "song": 0,
      "timbre": [
        {
          "label": "Female",
          "probability": 95
        },
        {
          "label": "Queen",
          "probability": 12
        },
        {
          "label": "Mature Woman",
          "probability": 37
        },
        {
          "label": "Young Woman",
          "probability": 56
        },
        {
          "label": "Middle-aged Woman",
          "probability": 67
        },
        {
          "label": "Loli",
          "probability": 24
        }
      ]
    },
    "audioText": "Recognized audio text content...",
    "audioTime": 10,
    "code": 1100,
    "requestParams": {
      "channel": "TEST",
      "lang": "zh",
      "returnAllText": 1,
      "tokenId": "test01"
    },
    "riskLevel": "REJECT"
  }
}

API Description

Audio Requirements

Timeout

Request

Request URL

Request Parameters

Risk Detection Types

Business Detection Types

data Object

User Levels

Response

Response Parameters

Response Codes

detail Object

audioDetail Array

Segment allLabels

Segment riskDetail

Segment businessLabels

audioTags Object

Language Labels

Examples

Request Example

Response Example

`data` Object

`detail` Object

`audioDetail` Array

Segment `allLabels`

Segment `riskDetail`

Segment `businessLabels`

`audioTags` Object