> ## Documentation Index > Fetch the complete documentation index at: https://blackbox.dasha.ai/llms.txt > Use this file to discover all available pages before exploring further. # Clone voice from audio > Creates a custom cloned voice from audio samples. The system analyzes the audio characteristics and generates a synthetic voice that mimics the original speaker. The cloned voice becomes available in your organization's voice library for use in agents. ## Audio Requirements * **Format**: WAV, MP3, or FLAC * **Quality**: Minimum 16kHz sample rate (44.1kHz recommended) * **Duration**: 30 seconds to 10 minutes of clear speech * **Content**: Clean speech without background noise or music * **Speaker**: Single speaker with consistent tone * **Total size**: Maximum 15MB combined ## Voice Cloning Process 1. **Audio analysis**: Extracts vocal characteristics and speech patterns 2. **Model training**: Creates custom voice model 3. **Quality validation**: Ensures voice meets quality standards 4. **Library storage**: Voice added to organization's library ## Use Cases * Branded voices for customer service * Personalized voice assistants * Multilingual deployment with consistent identity * Executive voice replication for announcements ## OpenAPI ````yaml https://blackbox.dasha.ai/swagger/v1/swagger.json post /api/v1/voice/clone openapi: 3.0.4 info: title: Dasha BlackBox Agent API description: API for managing AI agents and calls contact: name: DashaAI Team email: support@dasha.ai version: v1 servers: - url: https://blackbox.dasha.ai description: Dasha BlackBox Agent API security: - ApiKey: [] - OAuth: [] tags: - name: ActivityLogs - name: Agents - name: CallResults - name: Calls - name: Chats - name: Copilot - name: CustomerData - name: Mcp - name: Media - name: Misc - name: PronunciationDictionaries - name: Providers - name: SipAliases - name: SipCredentials - name: SipPhoneNumbers - name: TextChat - name: TwilioProvider - name: Voice - name: WebhookTest - name: WebIntegrations - name: WebSocket description: WebSocket endpoints for real-time communication paths: /api/v1/voice/clone: post: tags: - Voice summary: Clone voice from audio description: >- Creates a custom cloned voice from audio samples. The system analyzes the audio characteristics and generates a synthetic voice that mimics the original speaker. The cloned voice becomes available in your organization's voice library for use in agents. requestBody: content: multipart/form-data: schema: required: - Description - Language - Name - Provider type: object properties: Name: maxLength: 100 minLength: 1 type: string description: Display name for the cloned voice Description: maxLength: 1000 minLength: 1 type: string description: Description of voice characteristics and intended use Language: type: string description: >- Primary language for the voice model. The cloned voice will be optimized for this language. Provider: type: string description: >- Voice cloning provider to use for creating the voice model. Supported providers: ElevenLabs, Cartesia, Lmnt. ProviderSpecific.ElevenLabs.RemoveBackgroundNoise: type: boolean description: >- Whether to remove background noise from the audio sample during cloning for cleaner voice reproduction ProviderSpecific.Cartesia.Mode: type: string description: >- Cloning mode controlling the balance between voice stability and similarity. Supported values: "Stability", "Similarity". ProviderSpecific.Cartesia.Enhance: type: boolean description: >- Whether to apply audio enhancement during cloning for improved quality ProviderSpecific.Cartesia.Transcript: type: string description: >- Text transcript of the audio sample being cloned. Helps improve cloning accuracy. Labels: type: object additionalProperties: type: string description: >- Custom metadata labels for categorizing and organizing voices. Useful for filtering and searching cloned voices. audioFiles: type: array items: type: string format: binary description: Audio files for cloning encoding: Name: style: form Description: style: form Language: style: form Provider: style: form ProviderSpecific.ElevenLabs.RemoveBackgroundNoise: style: form ProviderSpecific.Cartesia.Mode: style: form ProviderSpecific.Cartesia.Enhance: style: form ProviderSpecific.Cartesia.Transcript: style: form Labels: style: form audioFiles: style: form responses: '201': description: Cloned voice created successfully content: application/json: schema: $ref: '#/components/schemas/TtsCloneResponseDto' '400': description: Invalid configuration or validation errors content: application/json: schema: $ref: '#/components/schemas/ProblemDetails' '401': description: Authentication failed or API key is missing content: application/json: schema: $ref: '#/components/schemas/ProblemDetails' '403': description: Access denied or quota exceeded content: application/json: schema: $ref: '#/components/schemas/ProblemDetails' '413': description: Audio files exceed size limit content: application/json: schema: $ref: '#/components/schemas/ProblemDetails' '422': description: Audio quality insufficient or processing failed content: application/json: schema: $ref: '#/components/schemas/ProblemDetails' '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/ProblemDetails' '500': description: Server error occurred during voice cloning components: schemas: TtsCloneResponseDto: required: - category - id - provider type: object properties: id: minLength: 1 type: string description: Unique identifier for the voice name: type: string description: Display name of the voice nullable: true voiceId: type: string description: Voice ID used for synthesis nullable: true provider: minLength: 1 type: string description: >- TTS provider used for this voice. Supported providers: ElevenLabs, Cartesia, Lmnt. description: type: string description: Description of voice characteristics nullable: true language: type: string description: Primary language for the voice nullable: true labels: type: object additionalProperties: type: string description: Custom metadata labels nullable: true previewUrl: type: string description: URL for voice preview audio nullable: true category: allOf: - $ref: '#/components/schemas/TtsVoiceCategory' description: >- Voice category. Public voices are provided by the TTS provider, Cloned voices are custom voices created through voice cloning. createdTime: type: string description: Timestamp when voice was created format: date-time nullable: true lastUpdatedTime: type: string description: Timestamp when voice was last updated format: date-time nullable: true additionalProperties: false description: Response DTO for TTS voice cloning operations ProblemDetails: type: object properties: type: type: string nullable: true title: type: string nullable: true status: type: integer format: int32 nullable: true detail: type: string nullable: true instance: type: string nullable: true additionalProperties: {} TtsVoiceCategory: enum: - Public - Cloned type: string description: Voice category classification securitySchemes: ApiKey: type: http description: API Key Authentication (Bearer {key}) scheme: Bearer OAuth: type: oauth2 flows: implicit: authorizationUrl: https://auth.dasha.ai/connect/authorize scopes: platform_api: Platform API ````