> ## 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. # Synthesize text to speech > Converts text to speech audio using the specified voice configuration. Returns MP3 audio ready for playback or download. Useful for voice preview during agent configuration and testing voice quality before deployment. ## OpenAPI ````yaml https://blackbox.dasha.ai/swagger/v1/swagger.json post /api/v1/voice/synthesize 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: AgentTestCases - 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/synthesize: post: tags: - Voice summary: Synthesize text to speech description: >- Converts text to speech audio using the specified voice configuration. Returns MP3 audio ready for playback or download. Useful for voice preview during agent configuration and testing voice quality before deployment. requestBody: description: Text synthesis configuration content: application/json: schema: allOf: - $ref: '#/components/schemas/TTSSynthesisRequest' description: Text-to-speech synthesis request configuration text/json: schema: allOf: - $ref: '#/components/schemas/TTSSynthesisRequest' description: Text-to-speech synthesis request configuration application/*+json: schema: allOf: - $ref: '#/components/schemas/TTSSynthesisRequest' description: Text-to-speech synthesis request configuration responses: '200': description: Returns synthesized audio as MP3 successfully content: application/json: schema: type: string format: binary '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 to synthesis or voice resources content: application/json: schema: $ref: '#/components/schemas/ProblemDetails' '413': description: Text content exceeds maximum length 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 synthesis components: schemas: TTSSynthesisRequest: required: - language - model - provider - text - voiceId type: object properties: text: maxLength: 5000 minLength: 1 type: string description: Text content to convert to speech voiceId: minLength: 1 type: string description: >- Voice identifier for synthesis. Use a cloned voice ID or public voice ID from the available voices. model: type: string description: >- TTS model to use for synthesis. Model availability depends on the provider. nullable: true language: minLength: 1 type: string description: >- Language code for synthesis. Format depends on provider (e.g., "en", "en-US"). speed: type: number description: >- Speech speed multiplier. Value of 1.0 is normal speed, values less than 1.0 are slower, values greater than 1.0 are faster. format: double provider: minLength: 1 type: string description: TTS provider name to use for synthesis vendorSpecific: type: object additionalProperties: type: string description: >- Provider-specific configuration options. Each provider supports different options. Consult provider documentation for available settings. nullable: true inlinePronunciationRules: type: array items: oneOf: - $ref: '#/components/schemas/AliasPronunciationRule' - $ref: '#/components/schemas/PhonemePronunciationRule' description: >- Base class for pronunciation rules that control how specific text is spoken during TTS synthesis. Rules use polymorphic serialization with a type discriminator to support different pronunciation methods (alias or phonetic). description: >- Inline pronunciation rules for preview support. These rules are applied during synthesis without being stored in a dictionary. nullable: true pronunciationDictionaryId: type: string description: >- Pronunciation dictionary ID to use for synthesis. When provided, the dictionary rules will be applied during synthesis. nullable: true additionalProperties: false description: Text-to-speech synthesis request configuration 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: {} AliasPronunciationRule: allOf: - $ref: '#/components/schemas/PronunciationRuleBase' - required: - alias - type type: object properties: type: enum: - alias type: string description: >- Rule type discriminator indicating this is an alias-based pronunciation rule. readOnly: true alias: minLength: 1 type: string description: >- Alternative text to speak instead of the matched text. The TTS engine will pronounce this replacement text using its natural language processing. For example, "HTTP" could be aliased to "H T T P" for letter-by-letter pronunciation, or "SQL" to "sequel" for word pronunciation. additionalProperties: false description: >- Alias pronunciation rule that replaces matched text with alternative text during TTS synthesis. Useful for expanding acronyms, replacing technical terms with pronounceable alternatives, or substituting brand names with phonetic spellings. The TTS engine will then pronounce the alias text naturally. PhonemePronunciationRule: allOf: - $ref: '#/components/schemas/PronunciationRuleBase' - required: - phoneme - type type: object properties: type: enum: - phoneme type: string description: >- Rule type discriminator indicating this is a phoneme-based pronunciation rule. readOnly: true phoneme: type: array items: type: string description: >- List of phoneme symbols representing how the text should be pronounced. Each string in the list is a phoneme from the specified phonetic alphabet. The TTS engine will synthesize these phonemes directly, bypassing its natural language processing for precise pronunciation control. alphabet: type: string description: >- Phonetic alphabet system used for the phoneme symbols. Supported values vary by provider but commonly include "ipa" (International Phonetic Alphabet). When not specified, the provider's default alphabet is used. nullable: true additionalProperties: false description: >- Phoneme pronunciation rule that specifies exact phonetic pronunciation for matched text using phonetic alphabet symbols. Provides precise control over pronunciation, useful for words that TTS engines commonly mispronounce, foreign words, or specialized terminology requiring specific pronunciation. PronunciationRuleBase: required: - text - type type: object properties: type: allOf: - $ref: '#/components/schemas/PronunciationRuleType' description: >- Rule type discriminator determining the pronunciation method. Supported values: alias (text replacement), phoneme (phonetic representation). readOnly: true text: minLength: 1 type: string description: >- Word or phrase to match in the input text. When this text is encountered during TTS synthesis, it will be pronounced according to the rule's pronunciation specification. Matching is typically case-insensitive. additionalProperties: false description: >- Base class for pronunciation rules that control how specific text is spoken during TTS synthesis. Rules use polymorphic serialization with a type discriminator to support different pronunciation methods (alias or phonetic). PronunciationRuleType: enum: - unspecified - alias - phoneme type: string description: >- Pronunciation rule type determining how matched text is pronounced during TTS synthesis. Each type uses a different method to specify pronunciation: alias substitutes alternative text, while phoneme uses phonetic symbols for precise pronunciation control. 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 ````