> ## 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. # Arcana v3 (Spanish) > Text-to-Speech API for generating Spanish speech using Rime Arcana v3 TTS model. Establishes a WebSocket connection for real-time text-to-speech. ## AsyncAPI ````yaml api-reference/asyncapi/tts-slng.asyncapi.yaml /v1/tts/slng/rime/arcana:3-es id: /v1/tts/slng/rime/arcana:3-es title: Arcana v3 (Spanish) description: >- Text-to-Speech API for generating Spanish speech using Rime Arcana v3 TTS model. Establishes a WebSocket connection for real-time text-to-speech. servers: - id: production protocol: wss host: api.slng.ai bindings: [] variables: [] address: /v1/tts/slng/rime/arcana:3-es parameters: [] bindings: - protocol: ws version: latest value: method: GET headers: type: object properties: X-Region-Override: type: string description: >- Target region override. Auto-selected if not provided. Available regions: `eu-north-1`. enum: - eu-north-1 x-parser-schema-id: x-parser-schema-id: WebsocketHeadersSlngArcanaV3Es schemaProperties: - name: method type: string description: GET required: false - name: headers type: object required: false properties: - name: X-Region-Override type: string description: >- Target region override. Auto-selected if not provided. Available regions: `eu-north-1`. enumValues: - eu-north-1 required: false operations: - &ref_1 id: ttsRimeArcana3EsReceiveInit title: Tts rime arcana3 es receive init description: Initialize session on Arcana v3 (Spanish) type: receive messages: - &ref_9 id: SlngRimeArcana3TtsInitRequestEs contentType: application/json payload: - name: Init Request (Rime Arcana v3 Spanish) description: Initialize a Spanish Rime Arcana v3 TTS session. type: object properties: - name: type type: string description: init required: true - name: model type: string description: The model identifier. required: true - name: speaker type: string description: Voice speaker ID for Rime Arcana v3 Spanish. enumValues: - aurelio - celestino - lark - luz - mar - nova - pola - seraphina - sirius - ursa required: true - name: config type: object description: Audio configuration settings for Rime Arcana TTS. 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: - mp3 - mulaw - pcm required: false - name: speed type: number description: >- Speech rate multiplier (0.25 = half speed, 2.0 = double speed). required: false - name: segment type: string description: >- Controls text segmentation for synthesis. 'immediate' synthesizes without waiting, 'never' waits for explicit flush/EOS, 'bySentence' waits for complete sentences. enumValues: - immediate - never - bySentence required: false - name: modelId type: string description: >- Model: arcana (most realistic, ~150ms), mistv2 (speed & control, ~70ms). enumValues: - arcana - arcana-3 - mistv2 - mist required: false - name: language type: string description: Language code. enumValues: - en - es - fr - de - ar - he - hi - ja - pt required: false - name: repetition_penalty type: number description: >- The repetition penalty. We do not recommend changing this from the default value. Typical range is 1 to 2. Float that penalizes new tokens based on whether they appear in the prompt and the generated text so far. Values > 1 encourage the model to use new tokens, while values < 1 encourage the model to repeat tokens. required: false - name: temperature type: number description: >- The temperature. We do not recommend changing this from the default value. Typical range is 0 to 1. Float that controls the randomness of the sampling. Lower values make the model more deterministic, while higher values make the model more random. Zero means greedy sampling. required: false - name: top_p type: number description: >- The top p. We do not recommend changing this from the default value. Typical range is 0 to 1. Float that controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to 1 to consider all tokens. required: false headers: [] jsonPayloadSchema: type: object description: Initialize a Spanish Rime Arcana v3 TTS session. required: - type - model - speaker properties: type: type: string const: init x-parser-schema-id: model: type: string description: The model identifier. x-parser-schema-id: speaker: type: string description: Voice speaker ID for Rime Arcana v3 Spanish. default: seraphina enum: - aurelio - celestino - lark - luz - mar - nova - pola - seraphina - sirius - ursa x-parser-schema-id: SlngRimeArcana3SpeakerEs config: type: object description: Audio configuration settings for Rime Arcana TTS. properties: sample_rate: type: integer description: Audio sample rate in Hz. enum: - 8000 - 16000 - 22050 - 24000 - 32000 - 44100 - 48000 default: 24000 x-parser-schema-id: encoding: type: string description: Audio encoding format. enum: - mp3 - mulaw - pcm default: pcm x-parser-schema-id: speed: type: number description: >- Speech rate multiplier (0.25 = half speed, 2.0 = double speed). minimum: 0.25 maximum: 2 default: 1 x-parser-schema-id: segment: type: string description: >- Controls text segmentation for synthesis. 'immediate' synthesizes without waiting, 'never' waits for explicit flush/EOS, 'bySentence' waits for complete sentences. enum: - immediate - never - bySentence default: bySentence x-parser-schema-id: modelId: type: string description: >- Model: arcana (most realistic, ~150ms), mistv2 (speed & control, ~70ms). enum: - arcana - arcana-3 - mistv2 - mist default: arcana x-parser-schema-id: language: type: string description: Language code. enum: - en - es - fr - de - ar - he - hi - ja - pt default: en x-parser-schema-id: x-parser-schema-id: SlngRimeArcana2TtsConfig repetition_penalty: type: number format: float default: 1.5 description: >- The repetition penalty. We do not recommend changing this from the default value. Typical range is 1 to 2. Float that penalizes new tokens based on whether they appear in the prompt and the generated text so far. Values > 1 encourage the model to use new tokens, while values < 1 encourage the model to repeat tokens. x-parser-schema-id: temperature: type: number format: float default: 0.5 description: >- The temperature. We do not recommend changing this from the default value. Typical range is 0 to 1. Float that controls the randomness of the sampling. Lower values make the model more deterministic, while higher values make the model more random. Zero means greedy sampling. x-parser-schema-id: top_p: type: number format: float default: 1 description: >- The top p. We do not recommend changing this from the default value. Typical range is 0 to 1. Float that controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to 1 to consider all tokens. x-parser-schema-id: x-parser-schema-id: title: Init Request (Rime Arcana v3 Spanish) description: Initialize a Spanish Rime Arcana v3 TTS session. example: |- { "type": "init", "model": "rime/arcana:3-es", "speaker": "seraphina", "config": { "modelId": "arcana-3", "language": "es", "sample_rate": 24000, "encoding": "pcm" } } bindings: [] extensions: - id: x-parser-unique-object-id value: SlngRimeArcana3TtsInitRequestEs bindings: [] extensions: &ref_0 - id: x-parser-unique-object-id value: /v1/tts/slng/rime/arcana:3-es - &ref_2 id: ttsRimeArcana3EsReceiveText title: Tts rime arcana3 es receive text description: Send text to Arcana v3 (Spanish) type: receive messages: - &ref_10 id: SlngRimeArcana3TtsTextMessage contentType: application/json payload: - name: Text Message (Arcana v3) description: Send text to synthesize using Rime Arcana v3. type: object properties: - name: type type: string description: text required: true - name: text type: string description: The text to synthesize. Maximum 500 characters per message. required: true headers: [] jsonPayloadSchema: type: object description: >- Send text to synthesize into audio output using Rime Arcana v3. Text accumulates in a buffer until punctuation is encountered. Synthesis begins when sufficient tokens exist for natural prosody. Use the flush message to force synthesis of buffered content. required: - type - text properties: type: type: string const: text x-parser-schema-id: text: type: string description: The text to synthesize. Maximum 500 characters per message. x-parser-schema-id: x-parser-schema-id: title: Text Message (Arcana v3) description: Send text to synthesize using Rime Arcana v3. example: |- { "type": "text", "text": "Hello from Rime Arcana v3. Testing text-to-speech synthesis." } bindings: [] extensions: - id: x-parser-unique-object-id value: SlngRimeArcana3TtsTextMessage bindings: [] extensions: *ref_0 - &ref_3 id: ttsRimeArcana3EsReceiveFlush title: Tts rime arcana3 es receive flush description: Flush buffered output on Arcana v3 (Spanish) type: receive messages: - &ref_11 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: ttsRimeArcana3EsReceiveClear title: Tts rime arcana3 es receive clear description: Clear queued output on Arcana v3 (Spanish) type: receive messages: - &ref_12 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: ttsRimeArcana3EsReceiveClose title: Tts rime arcana3 es receive close description: Close session on Arcana v3 (Spanish) type: receive messages: - &ref_13 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: ttsRimeArcana3EsSendAudioChunk title: Tts rime arcana3 es send audio chunk description: Receive audio chunk from Arcana v3 (Spanish) type: send messages: - &ref_14 id: SlngRimeArcanaTtsAudioChunk contentType: application/json payload: - name: Audio Chunk (Rime Arcana) description: Chunk of base64-encoded audio data from Rime Arcana TTS. type: object properties: - name: type type: string description: audio_chunk required: true - name: data type: string description: Base64-encoded audio data. required: true - name: contextId type: string description: >- Context ID for tracking. Matches the most recent contextId sent by the client at the time of audio generation. required: false headers: [] jsonPayloadSchema: type: object description: Chunk of base64-encoded audio data from Rime Arcana TTS. required: - type - data properties: type: type: string const: audio_chunk x-parser-schema-id: data: type: string format: byte description: Base64-encoded audio data. x-parser-schema-id: contextId: type: string nullable: true description: >- Context ID for tracking. Matches the most recent contextId sent by the client at the time of audio generation. x-parser-schema-id: x-parser-schema-id: title: Audio Chunk (Rime Arcana) description: Chunk of base64-encoded audio data from Rime Arcana TTS. example: |- { "type": "audio_chunk", "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEA...", "contextId": "ctx_abc123" } bindings: [] extensions: - id: x-parser-unique-object-id value: SlngRimeArcanaTtsAudioChunk bindings: [] extensions: *ref_0 - &ref_7 id: ttsRimeArcana3EsSendTimestamps title: Tts rime arcana3 es send timestamps description: Receive word timestamps from Arcana v3 (Spanish) type: send messages: - &ref_15 id: SlngRimeArcanaTtsTimestamps contentType: application/json payload: - name: Timestamps (Rime Arcana) description: Word-level timing data for synthesized audio from Rime Arcana. type: object properties: - name: type type: string description: timestamps required: true - name: word_timestamps type: object description: Word-level timestamp data. required: true properties: - name: words type: array description: Array of words. required: true properties: - name: item type: string required: false - name: start type: array description: Start times in seconds for each word. required: true properties: - name: item type: number required: false - name: end type: array description: End times in seconds for each word. required: true properties: - name: item type: number required: false headers: [] jsonPayloadSchema: type: object description: >- Word-level timing data for synthesized audio. Useful for interruption handling and lip-sync. required: - type - word_timestamps properties: type: type: string const: timestamps x-parser-schema-id: word_timestamps: type: object description: Word-level timestamp data. required: - words - start - end properties: words: type: array items: type: string x-parser-schema-id: description: Array of words. x-parser-schema-id: start: type: array items: type: number x-parser-schema-id: description: Start times in seconds for each word. x-parser-schema-id: end: type: array items: type: number x-parser-schema-id: description: End times in seconds for each word. x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: title: Timestamps (Rime Arcana) description: Word-level timing data for synthesized audio from Rime Arcana. example: |- { "type": "timestamps", "word_timestamps": { "words": [ "Hello", "from", "Arcana" ], "start": [ 0, 0.32, 0.58 ], "end": [ 0.31, 0.57, 1.02 ] } } bindings: [] extensions: - id: x-parser-unique-object-id value: SlngRimeArcanaTtsTimestamps bindings: [] extensions: *ref_0 - &ref_8 id: ttsRimeArcana3EsSendError title: Tts rime arcana3 es send error description: Receive error from Arcana v3 (Spanish) type: send messages: - &ref_16 id: SlngRimeArcanaTtsError contentType: application/json payload: - name: Error Response (Rime Arcana) description: Indicates an error occurred during Rime Arcana TTS synthesis. type: object properties: - name: type type: string description: error required: true - name: message type: string description: Human-readable error description. required: true headers: [] jsonPayloadSchema: type: object description: >- Indicates an error occurred during Rime Arcana TTS synthesis. Connection remains open after errors. required: - type - message properties: type: type: string const: error x-parser-schema-id: message: type: string description: Human-readable error description. x-parser-schema-id: x-parser-schema-id: title: Error Response (Rime Arcana) description: Indicates an error occurred during Rime Arcana TTS synthesis. example: |- { "type": "error", "message": "Text is too long. Maximum 500 characters per request." } bindings: [] extensions: - id: x-parser-unique-object-id value: SlngRimeArcanaTtsError bindings: [] extensions: *ref_0 sendOperations: - *ref_1 - *ref_2 - *ref_3 - *ref_4 - *ref_5 receiveOperations: - *ref_6 - *ref_7 - *ref_8 sendMessages: - *ref_9 - *ref_10 - *ref_11 - *ref_12 - *ref_13 receiveMessages: - *ref_14 - *ref_15 - *ref_16 extensions: - id: x-parser-unique-object-id value: /v1/tts/slng/rime/arcana:3-es 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: [] ````