> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aihubmax.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Paraformer V2 Speech Recognition

> - Paraformer V2 audio file recognition model, supports Chinese (including dialects), English, Japanese, and other languages
- Supports speaker diarization, hot word customization, and disfluency filtering
- Asynchronous processing mode, use the returned task ID to [query status](/pages/en/api-manual/task-management/get-task-detail)
- Recognition results are returned in the `results` field of the task detail




## OpenAPI

````yaml openapi/en/paraformer-v2.json POST /v1/audios/generations
openapi: 3.1.0
info:
  title: Paraformer V2 Speech Recognition
  version: '1.0'
servers:
  - url: https://api.aihubmax.com
security:
  - BearerAuth: []
paths:
  /v1/audios/generations:
    post:
      tags:
        - Audio > Speech Recognition
      summary: Paraformer V2 Speech Recognition
      description: >
        - Paraformer V2 audio file recognition model, supports Chinese
        (including dialects), English, Japanese, and other languages

        - Supports speaker diarization, hot word customization, and disfluency
        filtering

        - Asynchronous processing mode, use the returned task ID to [query
        status](/pages/en/api-manual/task-management/get-task-detail)

        - Recognition results are returned in the `results` field of the task
        detail
      operationId: paraformer-v2
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ParaformerRequest'
            examples:
              basic_transcription_with_default_settings:
                summary: Basic transcription with default settings
                value:
                  model: paraformer-v2
                  file_urls:
                    - https://example.com/audio/meeting.wav
              multi_language_transcription_with_diarization:
                summary: Multi-language transcription with diarization
                value:
                  model: paraformer-v2
                  file_urls:
                    - https://example.com/audio/interview_part1.mp3
                    - https://example.com/audio/interview_part2.mp3
                  language_hints:
                    - zh
                    - en
                  diarization:
                    enabled: true
                    speaker_count: 3
              8khz_telephone_audio_with_recognition_tuning:
                summary: 8kHz telephone audio with recognition tuning
                value:
                  model: paraformer-8k-v2
                  file_urls:
                    - https://example.com/audio/call_recording.wav
                  channel_id:
                    - 0
                    - 1
                  recognition:
                    disfluency_removal_enabled: true
                    vocabulary_id: vocab-xxxx
      responses:
        '200':
          $ref: '#/components/responses/TaskCreated'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/PaymentRequired'
        '422':
          $ref: '#/components/responses/UnprocessableEntity'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
        '503':
          $ref: '#/components/responses/ServiceUnavailable'
components:
  schemas:
    ParaformerRequest:
      type: object
      required:
        - model
        - file_urls
      properties:
        model:
          description: >-
            `paraformer-v2`: Supports Chinese, English, Japanese, and other
            languages

            `paraformer-8k-v2`: 8kHz sample rate, Chinese only
          examples:
            - paraformer-v2
            - paraformer-8k-v2
          type: string
          default: paraformer-v2
        file_urls:
          description: >
            Audio file URL list


            **Notes:**

            - Supports publicly accessible URLs via HTTP/HTTPS

            - Up to 100 URLs per request

            - Supported formats: aac, amr, avi, flac, flv, m4a, mkv, mov, mp3,
            mp4, mpeg, ogg, opus, wav, webm, wma, wmv

            - Single file must not exceed 2GB and 12 hours in duration
          items:
            type: string
          maxItems: 100
          minItems: 1
          type: array
          example:
            - https://example.com/audio/meeting.wav
        language_hints:
          anyOf:
            - items:
                type: string
              type: array
            - type: 'null'
          default: null
          description: >
            Language hints for recognition


            **Notes:**

            - Only supported by `paraformer-v2`, not applicable to
            `paraformer-8k-v2`

            - Supported language codes: `zh` (Chinese), `en` (English), `ja`
            (Japanese), `yue` (Cantonese), `ko` (Korean), `de` (German), `fr`
            (French), `ru` (Russian)
          x-unsupported-models:
            - paraformer-8k-v2
          example:
            - zh
            - en
        channel_id:
          anyOf:
            - items:
                type: integer
              type: array
            - type: 'null'
          default: null
          description: |-
            Audio track index

            **Notes:**
            - Index starts from 0, `[0]` means the first track
            - Default is `[0]` (only process the first track)
            - Each specified track is billed independently


            > Do not pass this parameter unless necessary.
          x-advanced: true
          example:
            - 0
        recognition:
          anyOf:
            - description: Recognition configuration settings.
              properties:
                disfluency_removal_enabled:
                  anyOf:
                    - type: boolean
                    - type: 'null'
                  default: null
                  description: >
                    Disfluency filtering


                    **Notes:**

                    - When enabled, filler words (e.g. "um", "uh") will be
                    filtered from recognition results

                    - Disabled by default
                  example: false
                timestamp_alignment_enabled:
                  anyOf:
                    - type: boolean
                    - type: 'null'
                  default: null
                  description: |
                    Timestamp alignment

                    **Notes:**
                    - When enabled, improves timestamp alignment accuracy
                    - Disabled by default
                  example: false
                vocabulary_id:
                  anyOf:
                    - type: string
                    - type: 'null'
                  default: null
                  description: >
                    Hot word vocabulary ID


                    **Notes:**

                    - The vocabulary ID created using the DashScope custom hot
                    word feature

                    - Only supported by v2 series models
                  example: vocab-xxxx
                special_word_filter:
                  anyOf:
                    - type: string
                    - type: 'null'
                  default: null
                  description: >
                    Sensitive word filter rules (JSON string)


                    **Notes:**

                    - If not provided, the system's built-in sensitive word
                    filter is used

                    - Pass a JSON string to customize replacement/removal rules
                  example: >-
                    {"filter_with_signed":{"word_list":["test"]},"system_reserved_filter":true}
              type: object
            - type: 'null'
          default: null
          description: >-
            Recognition configuration


            **Notes:**

            - Includes disfluency filtering, timestamp alignment, hot words, and
            sensitive word filter settings

            - If not provided, default configuration is used



            > Do not pass this parameter unless necessary.
          x-advanced: true
        diarization:
          anyOf:
            - description: Speaker diarization configuration.
              properties:
                enabled:
                  anyOf:
                    - type: boolean
                    - type: 'null'
                  default: null
                  description: >
                    Speaker diarization toggle


                    **Notes:**

                    - When enabled, recognition results will include the
                    `speaker_id` field

                    - Only applicable to mono audio

                    - Disabled by default
                  example: false
                speaker_count:
                  anyOf:
                    - maximum: 100
                      minimum: 2
                      type: integer
                    - type: 'null'
                  default: null
                  description: >
                    Speaker count hint


                    **Notes:**

                    - Range: `2` - `100`

                    - Requires speaker diarization to be enabled (`enabled:
                    true`)

                    - This is only a hint; the output is not guaranteed to match
                    this number exactly
                  example: 2
              type: object
            - type: 'null'
          default: null
          description: |-
            Speaker diarization configuration

            **Notes:**
            - Includes diarization toggle and speaker count hint
            - If not provided, speaker diarization is not enabled


            > Do not pass this parameter unless necessary.
          x-advanced: true
    TaskResponse:
      type: object
      properties:
        created:
          type: integer
          description: Task creation timestamp
          example: 1757165031
        id:
          type: string
          description: Task ID
          example: task-unified-1757165031-uyujaw3d
        model:
          type: string
          description: Actual model name used
        object:
          type: string
          description: Specific task type
          enum:
            - audio.generation.task
        progress:
          type: integer
          description: Task progress percentage (0-100)
          minimum: 0
          maximum: 100
          example: 0
        status:
          type: string
          description: Task status
          enum:
            - pending
            - processing
            - completed
            - failed
          example: pending
        task_info:
          type: object
          description: Asynchronous task info
          properties:
            can_cancel:
              type: boolean
              description: Whether the task can be cancelled
              example: true
            estimated_time:
              type: integer
              description: Estimated completion time (seconds)
              example: 45
        type:
          type: string
          description: Task output type
          enum:
            - audio
          example: audio
    ErrorResponse400:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              example: Invalid request format
            type:
              type: string
              example: invalid_request_error
    ErrorResponse401:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              example: Invalid API key
            type:
              type: string
              example: authentication_error
    ErrorResponse402:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              example: Insufficient account balance
            type:
              type: string
              example: insufficient_quota
    ErrorResponse422:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              example: Parameter validation failed
            type:
              type: string
              example: validation_error
    ErrorResponse429:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              example: Rate limit exceeded
            type:
              type: string
              example: rate_limit_error
    ErrorResponse500:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              example: Internal server error
            type:
              type: string
              example: server_error
    ErrorResponse503:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              example: Service temporarily unavailable, please try again later
            type:
              type: string
              example: service_unavailable
  responses:
    TaskCreated:
      description: Task created successfully
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/TaskResponse'
    BadRequest:
      description: Invalid request format
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse400'
    Unauthorized:
      description: Unauthorized
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse401'
    PaymentRequired:
      description: Insufficient balance
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse402'
    UnprocessableEntity:
      description: Parameter validation failed
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse422'
    TooManyRequests:
      description: Rate limit exceeded
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse429'
    InternalServerError:
      description: Internal server error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse500'
    ServiceUnavailable:
      description: Service temporarily unavailable
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse503'
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: |
        ## All APIs require Bearer Token authentication ##

        Add to request header:

        `Authorization: Bearer YOUR_API_KEY`

````