> ## Documentation Index > Fetch the complete documentation index at: https://docs.slng.ai/llms.txt > Use this file to discover all available pages before exploring further. # Aura 2 > Stream low-latency conversational text-to-speech from Deepgram Aura 2 over WebSocket as raw binary frames, optimized for ultra-low-latency voice agents. ## AsyncAPI ````yaml api-reference/asyncapi/tts-deepgram.asyncapi.yaml /v1/tts/deepgram/aura:2 id: /v1/tts/deepgram/aura:2 title: Aura 2 description: >- Stream low-latency conversational text-to-speech from Deepgram Aura 2 over WebSocket as raw binary frames, optimized for ultra-low-latency voice agents. servers: - id: production protocol: wss host: api.slng.ai bindings: [] variables: [] - id: staging protocol: wss host: stageapi.slng.ai bindings: [] variables: [] address: /v1/tts/deepgram/aura:2 parameters: [] bindings: - protocol: ws version: latest value: method: GET headers: type: object properties: X-World-Part-Override: type: string description: >- Target world part override. Auto-selected if not provided. Available world parts: `na`, `eu`. enum: - na - eu x-parser-schema-id: x-parser-schema-id: WebsocketHeadersDeepgramAura schemaProperties: - name: method type: string description: GET required: false - name: headers type: object required: false properties: - name: X-World-Part-Override type: string description: >- Target world part override. Auto-selected if not provided. Available world parts: `na`, `eu`. enumValues: - na - eu required: false operations: - &ref_1 id: ttsDeepgramAura2ReceiveInit title: Tts deepgram aura2 receive init description: Initialize session on Aura 2 type: receive messages: - &ref_10 id: TtsInitRequest contentType: application/json payload: - name: Init Request description: Initialize a TTS session with model and voice configuration. type: object properties: - name: type type: string description: init required: true - name: model type: string description: TTS model identifier. enumValues: - aura:2 - eleven:3 - eleven-flash:2 - eleven-flash:2.5 - eleven-multilingual:2 - canopylabs/orpheus:en - deepgram/aura:2 - deepgram/aura:2-en - deepgram/aura:2-es - rime/arcana:3-en - rime/arcana:3-es - rime/arcana:3-hi - rime/arcana:ar - rime/arcana:de - rime/arcana:en - rime/arcana:es - rime/arcana:fr required: true - name: voice type: string description: Voice identifier required: false - name: config type: object description: Synthesis configuration options required: false properties: - name: sample_rate type: integer description: Audio sample rate in Hz. enumValues: - 8000 - 16000 - 22050 - 24000 - 32000 - 44100 - 48000 required: false - name: encoding type: string description: Audio encoding format enumValues: - linear16 - mp3 - opus required: false - name: language type: string description: ISO-639-1 language code. enumValues: - en - ja - zh - de - hi - fr - ko - pt - it - es - id - nl - tr - fil - pl - sv - bg - ro - ar - cs - el - fi - hr - ms - sk - da - ta - uk - ru - hu - 'no' - vi required: false - name: speed type: number description: Speech speed multiplier (e.g., 1.0 for normal) required: false headers: [] jsonPayloadSchema: type: object description: >- Initialize a session with model and voice configuration before sending text. required: - type - model properties: type: type: string const: init default: init x-parser-schema-id: model: type: string description: TTS model identifier. enum: - aura:2 - eleven:3 - eleven-flash:2 - eleven-flash:2.5 - eleven-multilingual:2 - canopylabs/orpheus:en - deepgram/aura:2 - deepgram/aura:2-en - deepgram/aura:2-es - rime/arcana:3-en - rime/arcana:3-es - rime/arcana:3-hi - rime/arcana:ar - rime/arcana:de - rime/arcana:en - rime/arcana:es - rime/arcana:fr x-parser-schema-id: TtsModel voice: type: string description: Voice identifier x-parser-schema-id: config: type: object description: Synthesis configuration options properties: sample_rate: type: integer description: Audio sample rate in Hz. enum: - 8000 - 16000 - 22050 - 24000 - 32000 - 44100 - 48000 x-parser-schema-id: SampleRate encoding: type: string description: Audio encoding format enum: - linear16 - mp3 - opus x-parser-schema-id: language: type: string description: ISO-639-1 language code. enum: - en - ja - zh - de - hi - fr - ko - pt - it - es - id - nl - tr - fil - pl - sv - bg - ro - ar - cs - el - fi - hr - ms - sk - da - ta - uk - ru - hu - 'no' - vi x-parser-schema-id: LanguageCode speed: type: number description: Speech speed multiplier (e.g., 1.0 for normal) x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: title: Init Request description: Initialize a TTS session with model and voice configuration. example: |- { "type": "init", "model": "aura:2", "voice": "aura-2-thalia-en", "config": { "sample_rate": 24000, "encoding": "linear16" } } bindings: [] extensions: - id: x-parser-unique-object-id value: TtsInitRequest bindings: [] extensions: &ref_0 - id: x-parser-unique-object-id value: /v1/tts/deepgram/aura:2 - &ref_2 id: ttsDeepgramAura2ReceiveText title: Tts deepgram aura2 receive text description: Send text to Aura 2 type: receive messages: - &ref_11 id: TtsTextMessage contentType: application/json payload: - name: Text Message description: Send text to synthesize into audio output. type: object properties: - name: type type: string description: text required: true - name: text type: string description: Text to synthesize required: true - name: flush type: boolean description: Whether to flush remaining audio immediately after this text required: false headers: [] jsonPayloadSchema: type: object description: Send text to synthesize into audio output. required: - type - text properties: type: type: string const: text x-parser-schema-id: text: type: string description: Text to synthesize x-parser-schema-id: flush: type: boolean description: Whether to flush remaining audio immediately after this text x-parser-schema-id: x-parser-schema-id: title: Text Message description: Send text to synthesize into audio output. example: |- { "type": "text", "text": "Hello, this is a test of text-to-speech synthesis." } bindings: [] extensions: - id: x-parser-unique-object-id value: TtsTextMessage bindings: [] extensions: *ref_0 - &ref_3 id: ttsDeepgramAura2ReceiveFlush title: Tts deepgram aura2 receive flush description: Flush buffered output on Aura 2 type: receive messages: - &ref_12 id: TtsFlushMessage contentType: application/json payload: - name: Flush Message description: Force any buffered text/audio to be finalized and delivered. type: object properties: - name: type type: string description: flush required: true headers: [] jsonPayloadSchema: type: object description: Force any buffered text/audio to be finalized and delivered. required: - type properties: type: type: string const: flush x-parser-schema-id: x-parser-schema-id: title: Flush Message description: Force any buffered text/audio to be finalized and delivered. example: |- { "type": "flush" } bindings: [] extensions: - id: x-parser-unique-object-id value: TtsFlushMessage bindings: [] extensions: *ref_0 - &ref_4 id: ttsDeepgramAura2ReceiveClear title: Tts deepgram aura2 receive clear description: Clear queued output on Aura 2 type: receive messages: - &ref_13 id: TtsClearMessage contentType: application/json payload: - name: Clear Message description: Clear any queued text/audio from the current session. type: object properties: - name: type type: string description: clear required: true headers: [] jsonPayloadSchema: type: object description: Clear any queued text/audio from the current session. required: - type properties: type: type: string const: clear x-parser-schema-id: x-parser-schema-id: title: Clear Message description: Clear any queued text/audio from the current session. example: |- { "type": "clear" } bindings: [] extensions: - id: x-parser-unique-object-id value: TtsClearMessage bindings: [] extensions: *ref_0 - &ref_5 id: ttsDeepgramAura2ReceiveClose title: Tts deepgram aura2 receive close description: Close session on Aura 2 type: receive messages: - &ref_14 id: TtsCloseMessage contentType: application/json payload: - name: Close Message description: Close the session and stop any further audio. type: object properties: - name: type type: string description: close required: true headers: [] jsonPayloadSchema: type: object description: Close the session and stop any further audio. required: - type properties: type: type: string const: close x-parser-schema-id: x-parser-schema-id: title: Close Message description: Close the session and stop any further audio. example: |- { "type": "close" } bindings: [] extensions: - id: x-parser-unique-object-id value: TtsCloseMessage bindings: [] extensions: *ref_0 - &ref_6 id: ttsDeepgramAura2SendBinaryAudio title: Tts deepgram aura2 send binary audio description: Receive binary audio from Aura 2 type: send messages: - &ref_15 id: DeepgramAuraTtsBinaryAudio contentType: application/octet-stream payload: - name: Binary Audio Frame description: Raw binary audio frame from Deepgram Aura. type: object properties: - name: type type: string description: >- Placeholder discriminator. The actual message is a raw binary WebSocket frame, not JSON. required: true headers: [] jsonPayloadSchema: type: object description: >- Raw binary audio data sent as a WebSocket binary frame. This is NOT a JSON message — it is a raw audio buffer. The encoding and sample rate match the query parameters used when opening the connection. The object schema below is for documentation purposes only as required by the AsyncAPI tooling. required: - type properties: type: type: string const: binary description: >- Placeholder discriminator. The actual message is a raw binary WebSocket frame, not JSON. x-parser-schema-id: x-parser-schema-id: title: Binary Audio Frame description: Raw binary audio frame from Deepgram Aura. example: >- "0000FF00000000FF00000000010101010101010100000000FFFFFFFFFFFEFEFDFEFEFEFEFDFDFEFEFEFEFEFEFEFEFEFFFFFFFFFEFEFEFEFF0001000001020303030303030303030201010000FFFFFEFDFDFDFDFEFFFFFFFF0001020303020201000000FFFDFCFBFAFAFBFAF9F8F7F7F7F6F6F4F2F2F3F7FC000406090F14191A19181715110E0A05FEF9F6F3F0EEECEBEBECEEF2F6F9FC0005090D0F101010100E0C080401" bindings: [] extensions: - id: x-parser-unique-object-id value: DeepgramAuraTtsBinaryAudio bindings: [] extensions: *ref_0 - &ref_7 id: ttsDeepgramAura2SendFlushed title: Tts deepgram aura2 send flushed description: Receive flushed confirmation from Aura 2 type: send messages: - &ref_16 id: TtsFlushed contentType: application/json payload: - name: Flushed description: Acknowledges that buffered output was flushed. type: object properties: - name: type type: string description: flushed required: true headers: [] jsonPayloadSchema: type: object description: Acknowledges that buffered output was flushed. required: - type properties: type: type: string const: flushed x-parser-schema-id: x-parser-schema-id: title: Flushed description: Acknowledges that buffered output was flushed. example: |- { "type": "flushed" } bindings: [] extensions: - id: x-parser-unique-object-id value: TtsFlushed bindings: [] extensions: *ref_0 - &ref_8 id: ttsDeepgramAura2SendCleared title: Tts deepgram aura2 send cleared description: Receive cleared confirmation from Aura 2 type: send messages: - &ref_17 id: TtsCleared contentType: application/json payload: - name: Cleared description: Acknowledges that queued output was cleared. type: object properties: - name: type type: string description: cleared required: true headers: [] jsonPayloadSchema: type: object description: Acknowledges that queued output was cleared. required: - type properties: type: type: string const: cleared x-parser-schema-id: x-parser-schema-id: title: Cleared description: Acknowledges that queued output was cleared. example: |- { "type": "cleared" } bindings: [] extensions: - id: x-parser-unique-object-id value: TtsCleared bindings: [] extensions: *ref_0 - &ref_9 id: ttsDeepgramAura2SendError title: Tts deepgram aura2 send error description: Receive error from Aura 2 type: send messages: - &ref_18 id: TtsErrorResponse contentType: application/json payload: - name: Error Response description: Indicates an error occurred during synthesis. type: object properties: - name: type type: string description: error required: true - name: code type: string description: Error code. enumValues: - auth_error - config_error - rate_limit - provider_error required: true - name: message type: string description: Human-readable error description required: true headers: [] jsonPayloadSchema: type: object description: Indicates an error occurred during synthesis. required: - type - code - message properties: type: type: string const: error x-parser-schema-id: code: type: string description: Error code. enum: - auth_error - config_error - rate_limit - provider_error x-parser-schema-id: message: type: string description: Human-readable error description x-parser-schema-id: x-parser-schema-id: title: Error Response description: Indicates an error occurred during synthesis. example: |- { "type": "error", "code": "provider_error", "message": "Provider returned an unexpected error" } bindings: [] extensions: - id: x-parser-unique-object-id value: TtsErrorResponse bindings: [] extensions: *ref_0 sendOperations: - *ref_1 - *ref_2 - *ref_3 - *ref_4 - *ref_5 receiveOperations: - *ref_6 - *ref_7 - *ref_8 - *ref_9 sendMessages: - *ref_10 - *ref_11 - *ref_12 - *ref_13 - *ref_14 receiveMessages: - *ref_15 - *ref_16 - *ref_17 - *ref_18 extensions: - id: x-parser-unique-object-id value: /v1/tts/deepgram/aura:2 securitySchemes: - id: bearer name: bearer type: http description: > API key issued by SLNG. Pass as `Authorization: Bearer ` in the WebSocket upgrade request headers. scheme: bearer extensions: [] ````