# Text to Speech with Word Timestamps ## OpenAPI Specification ```yaml openapi: 3.0.1 info: title: '' description: '' version: 1.0.0 paths: /text_to_speech/with_timestamps: post: summary: Text to Speech with Word Timestamps deprecated: false description: >- Generates speech using provided text and voice of your choice and returns audio and word timestamps. tags: - API Reference/Text-to-Speech parameters: - name: x-api-key in: header description: '' required: true example: schema: type: string - name: version in: header description: '' required: true example: v1 schema: type: string requestBody: content: application/json: schema: type: object properties: model_id: type: string description: Model id enum: - async_flash_v1.0 x-apidog-enum: - value: async_flash_v1.0 name: Async Flash v1.0 description: >- Fastest model, designed for real-time and low-latency applications transcript: type: string description: Text to convert to the speech voice: type: object properties: mode: type: string enum: - id x-apidog-enum: - value: id name: '' description: '' id: type: string description: Voice id required: - mode - id x-apidog-orders: - mode - id description: Voice to use while make speech output_format: type: object properties: container: type: string description: Output audio format enum: - raw - mp3 - wav x-apidog-enum: - value: raw name: '' description: '' - value: mp3 name: '' description: '' - value: wav name: '' description: '' encoding: type: string description: Output audio encoding. Ignore if mp3 enum: - pcm_f32le - pcm_s16le x-apidog-enum: - value: pcm_f32le name: '' description: '' - value: pcm_s16le name: '' description: '' default: pcm_s16le sample_rate: type: integer minimum: 8000 maximum: 48000 description: Output audio sample rate bit_rate: type: integer default: 192000 minimum: 32000 maximum: 320000 description: Output audio bit rate. Use only with mp3 required: - container - sample_rate x-apidog-orders: - container - encoding - sample_rate - bit_rate description: Output configurations language: type: string description: >- Force to synthesize speech in the specified language (ISO 639-1), regardless of the detected language of the input text. enum: - en - fr - es - de - it - pt - ar - ru - ro - ja - he - hy - tr - hi - zh x-apidog-enum: - value: en name: English description: '' - value: fr name: French description: '' - value: es name: Spanish description: '' - value: de name: German description: '' - value: it name: Italian description: '' - value: pt name: Portuguese description: '' - value: ar name: Arabic description: '' - value: ru name: Russian description: '' - value: ro name: Romanian description: '' - value: ja name: Japanese description: '' - value: he name: Hebrew description: '' - value: hy name: Armenian description: '' - value: tr name: Turkish description: '' - value: hi name: Hindi description: '' - value: zh name: Chinese description: '' speed_control: type: number minimum: 0.7 maximum: 2 title: (experimental) description: Adjusts the speaking speed of the synthesized voice. stability: type: integer minimum: 0 maximum: 100 title: (experimental) description: >- Adjusts how stable or expressive the synthesized voice sounds. required: - model_id - transcript - voice - output_format x-apidog-orders: - model_id - transcript - voice - output_format - language - speed_control - stability x-apidog-refs: {} example: model_id: async_flash_v1.0 transcript: Welcome to Async voice: mode: id id: e0f39dc4-f691-4e78-bba5-5c636692cc04 output_format: container: raw encoding: pcm_f32le sample_rate: 44100 responses: '200': openapi: 3.0.3 info: title: TTS Streaming API – Error Model version: 1.0.0 paths: /v1/tts/stream: post: summary: Stream speech audio responses: '400': $ref: '#/components/responses/VOICE_FIELD_UPDATE_NOT_ALLOWED' '401': $ref: '#/components/responses/INVALID_API_KEY' '404': $ref: '#/components/responses/VOICE_NOT_FOUND' '429': $ref: '#/components/responses/TOO_MANY_CONCURRENT_REQUESTS' '500': $ref: '#/components/responses/INTERNAL_SERVER_ERROR' components: schemas: ErrorResponse: type: object required: - message properties: error_code: type: string message: type: string extra: type: object additionalProperties: true InternalServerError: allOf: - $ref: '#/components/schemas/ErrorResponse' - type: object properties: method: type: string url: type: string format: uri detail: type: string responses: TOO_MANY_CONCURRENT_REQUESTS: description: Parallel request limit exceeded content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error_code: TOO_MANY_CONCURRENT_REQUESTS message: Too many concurrent requests extra: limit: 5 current: 7 RATE_LIMIT_EXCEEDED: description: Per‑minute request cap reached content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error_code: RATE_LIMIT_EXCEEDED message: Rate limit exceeded. Please try again later. extra: limit: 120 retry_after_ms: 8500 INVALID_API_KEY: description: Invalid or expired key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error_code: INVALID_API_KEY message: Invalid or expired API key. extra: api_key: sk_test_... TOKEN_NOT_FOUND: description: Supplied token ID does not exist content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' USAGE_LIMIT_EXCEEDED: description: Monthly quota exhausted content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' VOICE_NOT_FOUND: description: Requested voice ID is unknown content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' VOICE_FIELD_UPDATE_NOT_ALLOWED: description: Immutable voice field content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' VERSION_NOT_FOUND: description: Unknown API version content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' INVALID_LANGUAGE: description: Language code not supported content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' FORMAT_NOT_RECOGNIZED: description: Unsupported audio format content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' INTERNAL_SERVER_ERROR: description: Unhandled server‑side exception content: application/json: schema: $ref: '#/components/schemas/InternalServerError' example: message: Oops! Internal server error occurred. method: POST url: /v1/tts/stream detail: 'Error: Traceback #42' description: '' content: application/json: schema: type: object properties: audio_base64: type: string description: Audio file content base64 encoded alignment: type: object properties: words: type: array items: type: string word_start_times_milliseconds: type: array items: type: number word_end_times_milliseconds: type: array items: type: number x-apidog-orders: - words - word_start_times_milliseconds - word_end_times_milliseconds required: - words - word_end_times_milliseconds - word_start_times_milliseconds x-apidog-orders: - audio_base64 - alignment required: - audio_base64 - alignment example: audio_base64: ... alignment: words: - Welcome - to - Async word_start_times_milliseconds: - 0 - 871 - 923 word_end_times_milliseconds: - 871 - 900 - 1637 headers: {} x-apidog-name: Success '400': description: '' content: application/json: schema: type: object properties: detail: type: object properties: error_code: type: string message: type: string required: - error_code - message x-apidog-orders: - error_code - message required: - detail x-apidog-orders: - detail example: detail: error_code: INVALID_LANGUAGE message: Language code 'xx' is not supported. headers: {} x-apidog-name: INVALID_LANGUAGE '401': description: '' content: application/json: schema: type: object properties: detail: type: object properties: error_code: type: string message: type: string extra: type: object properties: api_key: type: string x-apidog-orders: - api_key required: - error_code - message x-apidog-orders: - error_code - message - extra required: - detail x-apidog-orders: - detail example: detail: error_code: INVALID_API_KEY message: Invalid or expired API key. extra: api_key: sk_33... headers: {} x-apidog-name: INVALID_API_KEY '404': description: '' content: application/json: schema: type: object properties: detail: type: object properties: error_code: type: string message: type: string extra: type: object properties: voice_id: type: string x-apidog-orders: - voice_id required: - error_code - message x-apidog-orders: - error_code - message - extra required: - detail x-apidog-orders: - detail example: detail: error_code: VOICE_NOT_FOUND message: Requested voice with ID 17c7… not found. extra: voice_id: 17c7… headers: {} x-apidog-name: VOICE_NOT_FOUND '429': description: '' content: application/json: schema: type: object properties: detail: type: object properties: error_code: type: string message: type: string extra: type: object properties: limit: type: integer current: type: integer x-apidog-orders: - limit - current required: - error_code - message x-apidog-orders: - error_code - message - extra required: - detail x-apidog-orders: - detail example: detail: error_code: TOO_MANY_CONCURRENT_REQUESTS message: Too many concurrent requests extra: limit: 5 current: 7 headers: {} x-apidog-name: TOO_MANY_CONCURRENT_REQUESTS '500': description: '' content: application/json: schema: type: object properties: message: type: string method: type: string url: type: string detail: type: string required: - message - method - url - detail x-apidog-orders: - message - method - url - detail example: message: Oops! Internal server error occurred. method: POST url: /v1/tts/stream detail: 'Error: Traceback #42' headers: {} x-apidog-name: Server Error x-429:RATE_LIMIT_EXCEEDED: description: '' content: application/json: schema: type: object properties: detail: type: object properties: error_code: type: string message: type: string extra: type: object properties: limit: type: integer retry_after_ms: type: integer x-apidog-orders: - limit - retry_after_ms required: - error_code - message x-apidog-orders: - error_code - message - extra required: - detail x-apidog-orders: - detail example: detail: error_code: RATE_LIMIT_EXCEEDED message: Rate limit exceeded. Please try again later. extra: limit: 120 retry_after_ms: 8500 headers: {} x-apidog-name: RATE_LIMIT_EXCEEDED x-429:USAGE_LIMIT_EXCEEDED: description: '' content: application/json: schema: type: object properties: detail: type: object properties: error_code: type: string message: type: string extra: type: object properties: limit: type: integer current: type: integer x-apidog-orders: - limit - current required: - error_code - message x-apidog-orders: - error_code - message - extra required: - detail x-apidog-orders: - detail example: detail: error_code: USAGE_LIMIT_EXCEEDED message: Quota exceeded. Please upgrade your plan or try later. extra: limit: 1000000 current: 1250000 headers: {} x-apidog-name: USAGE_LIMIT_EXCEEDED x-404:VERSION_NOT_FOUND: description: '' content: application/json: schema: type: object properties: detail: type: object properties: error_code: type: string message: type: string required: - error_code - message x-apidog-orders: - error_code - message required: - detail x-apidog-orders: - detail example: detail: error_code: VERSION_NOT_FOUND message: API version v0.9 not found. headers: {} x-apidog-name: VERSION_NOT_FOUND x-400:FORMAT_NOT_RECOGNIZED: description: '' content: application/json: schema: type: object properties: detail: type: object properties: error_code: type: string message: type: string required: - error_code - message x-apidog-orders: - error_code - message required: - detail x-apidog-orders: - detail example: detail: error_code: FORMAT_NOT_RECOGNIZED message: Audio format not recognized or unsupported. headers: {} x-apidog-name: FORMAT_NOT_RECOGNIZED security: [] x-apidog-folder: API Reference/Text-to-Speech x-apidog-status: released x-run-in-apidog: https://app.apidog.com/web/project/909580/apis/api-18761064-run components: schemas: {} securitySchemes: {} servers: [] security: [] ```