> ## Documentation Index > Fetch the complete documentation index at: https://docs.timepay.ai/llms.txt > Use this file to discover all available pages before exploring further. # Text to Speech (Websocket) > The WebSocket API provides real-time text-to-speech streaming capabilities with high-quality voice synthesis. This API uses WebSocket to deliver audio chunks as they’re generated, enabling low-latency audio playback ## AsyncAPI ````yaml asyncapi.yaml speech id: speech title: Speech Channel description: Channel for TTS requests and audio streaming responses servers: - id: production protocol: wss host: api.tts.timepay.ai bindings: [] variables: [] address: /api/v1/get_speech parameters: [] bindings: [] operations: - &ref_1 id: sendTTSRequest title: Send t t s request description: Send a TTS request type: receive messages: - &ref_3 id: TTSRequest contentType: application/json payload: - name: TTS Request description: Request to synthesize text to speech type: object properties: - name: type type: string description: Message type identifier required: true - name: text type: string description: The text to convert to speech required: true - name: voice_id type: string description: The specific voice ID to use for synthesis enumValues: - Ogbs15oBevLzXsUuTtA1 - Owbs15oBevLzXsUurdA_ - PAbs15oBevLzXsUu4dCi - PQbt15oBevLzXsUuNtD3 - Pgbt15oBevLzXsUubdA6 required: true - name: language type: string description: ISO language code enumValues: - en - hi - mr - ta - te - gu - kn - ml - bn - pa - od - as required: false - name: add_wav_header type: boolean description: >- If true, adds a WAV header to the stream for immediate playback required: false - name: sample_rate type: integer description: Audio sample rate in Hz enumValues: - 8000 - 16000 - 24000 required: false - name: speed type: number description: Playback speed multiplier (0.5 to 2.0, where 1.0 is normal) required: false - name: request_id type: string description: Optional custom identifier for tracking requests required: false headers: [] jsonPayloadSchema: type: object required: - type - text - voice_id properties: type: type: string description: Message type identifier const: speech example: speech x-parser-schema-id: text: type: string description: The text to convert to speech example: Hello, welcome to Vox. x-parser-schema-id: voice_id: type: string description: The specific voice ID to use for synthesis example: Ogbs15oBevLzXsUuTtA1 enum: - Ogbs15oBevLzXsUuTtA1 - Owbs15oBevLzXsUurdA_ - PAbs15oBevLzXsUu4dCi - PQbt15oBevLzXsUuNtD3 - Pgbt15oBevLzXsUubdA6 x-parser-schema-id: language: type: string description: ISO language code default: en example: en enum: - en - hi - mr - ta - te - gu - kn - ml - bn - pa - od - as x-parser-schema-id: add_wav_header: type: boolean description: If true, adds a WAV header to the stream for immediate playback default: true example: true x-parser-schema-id: sample_rate: type: integer description: Audio sample rate in Hz default: 24000 example: 24000 enum: - 8000 - 16000 - 24000 x-parser-schema-id: speed: type: number description: Playback speed multiplier (0.5 to 2.0, where 1.0 is normal) default: 1 minimum: 0.5 maximum: 2 example: 1 x-parser-schema-id: request_id: type: string description: Optional custom identifier for tracking requests example: req_12345 x-parser-schema-id: x-parser-schema-id: title: TTS Request description: Request to synthesize text to speech example: |- { "type": "", "text": "", "voice_id": "", "language": "", "add_wav_header": true, "sample_rate": 123, "speed": 123, "request_id": "" } bindings: [] extensions: - id: x-parser-unique-object-id value: TTSRequest bindings: [] extensions: &ref_0 - id: x-parser-unique-object-id value: speech - &ref_2 id: receiveTTSResponse title: Receive t t s response description: Receive TTS response type: send messages: - &ref_4 id: ConnectedResponse contentType: application/json payload: - name: Connected description: Sent immediately after successful WebSocket connection type: object properties: - name: type type: string description: connected required: true - name: connection_id type: string description: Unique identifier for this WebSocket connection required: true - name: message type: string description: Connection status message required: true headers: [] jsonPayloadSchema: type: object required: - type - connection_id - message properties: type: type: string const: connected example: connected x-parser-schema-id: connection_id: type: string description: Unique identifier for this WebSocket connection example: conn_abc123 x-parser-schema-id: message: type: string description: Connection status message example: Connected successfully x-parser-schema-id: x-parser-schema-id: title: Connected description: Sent immediately after successful WebSocket connection example: |- { "type": "", "connection_id": "", "message": "" } bindings: [] extensions: - id: x-parser-unique-object-id value: ConnectedResponse - &ref_5 id: AudioChunkResponse contentType: application/json payload: - name: Audio Chunk description: Streamed audio data. Multiple chunks are sent per request. type: object properties: - name: type type: string description: audio_chunk required: true - name: request_id type: string description: The request identifier required: true - name: chunk_index type: integer description: Zero-indexed position in the audio stream required: true - name: data type: string description: Base64-encoded audio data required: true headers: [] jsonPayloadSchema: type: object required: - type - request_id - chunk_index - data properties: type: type: string const: audio_chunk example: audio_chunk x-parser-schema-id: request_id: type: string description: The request identifier example: req_12345 x-parser-schema-id: chunk_index: type: integer description: Zero-indexed position in the audio stream example: 0 x-parser-schema-id: data: type: string format: byte description: Base64-encoded audio data example: UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAEAfAAABAAgA... x-parser-schema-id: x-parser-schema-id: title: Audio Chunk description: Streamed audio data. Multiple chunks are sent per request. example: |- { "type": "", "request_id": "", "chunk_index": 123, "data": "" } bindings: [] extensions: - id: x-parser-unique-object-id value: AudioChunkResponse - &ref_6 id: CompleteResponse contentType: application/json payload: - name: Complete description: Signals all audio has been sent type: object properties: - name: type type: string description: complete required: true - name: request_id type: string description: The request identifier required: true - name: total_chunks type: integer description: Total number of audio chunks sent required: true - name: characters type: integer description: Characters processed required: true headers: [] jsonPayloadSchema: type: object required: - type - request_id - total_chunks - characters properties: type: type: string const: complete example: complete x-parser-schema-id: request_id: type: string description: The request identifier example: req_12345 x-parser-schema-id: total_chunks: type: integer description: Total number of audio chunks sent example: 15 x-parser-schema-id: characters: type: integer description: Characters processed example: 22 x-parser-schema-id: x-parser-schema-id: title: Complete description: Signals all audio has been sent example: |- { "type": "", "request_id": "", "total_chunks": 123, "characters": 123 } bindings: [] extensions: - id: x-parser-unique-object-id value: CompleteResponse - &ref_7 id: ErrorResponse contentType: application/json payload: - name: Error description: Indicates a problem with the request type: object properties: - name: type type: string description: error required: true - name: request_id type: string description: The request identifier (if available) required: false - name: error type: string description: Error code for programmatic handling enumValues: - invalid_request - invalid_voice - invalid_language - text_too_long - concurrency_limit_exceeded - insufficient_credits - internal_error required: true - name: message type: string description: Human-readable error description required: true headers: [] jsonPayloadSchema: type: object required: - type - error - message properties: type: type: string const: error example: error x-parser-schema-id: request_id: type: string description: The request identifier (if available) example: req_12345 x-parser-schema-id: error: type: string description: Error code for programmatic handling example: concurrency_limit_exceeded enum: - invalid_request - invalid_voice - invalid_language - text_too_long - concurrency_limit_exceeded - insufficient_credits - internal_error x-parser-schema-id: message: type: string description: Human-readable error description example: Maximum concurrent requests (5) exceeded x-parser-schema-id: x-parser-schema-id: title: Error description: Indicates a problem with the request example: |- { "type": "", "request_id": "", "error": "", "message": "" } bindings: [] extensions: - id: x-parser-unique-object-id value: ErrorResponse bindings: [] extensions: *ref_0 sendOperations: - *ref_1 receiveOperations: - *ref_2 sendMessages: - *ref_3 receiveMessages: - *ref_4 - *ref_5 - *ref_6 - *ref_7 extensions: - id: x-parser-unique-object-id value: speech securitySchemes: - id: bearerAuth name: bearerAuth type: http description: Pass API key in Authorization header as Bearer token scheme: bearer extensions: [] ````