> ## Documentation Index > Fetch the complete documentation index at: https://docs.shuyou.ai/llms.txt > Use this file to discover all available pages before exploring further. # Inworld TTS 1.5 Max > Create asynchronous text-to-speech tasks with inworld-tts-1.5-max via POST /v1/predictions. ## Prompt (`input.prompt`) Required. Text to synthesize. Maximum **2,000** characters. ## Voice presets (`input.voice`) Optional. Default **`Craig (en)`**. Pass the voice ID exactly as listed (language tag in parentheses). | # | `voice` | | --- | ---------------- | | 1 | `Loretta (en)` | | 2 | `Darlene (en)` | | 3 | `Marlene (en)` | | 4 | `Hank (en)` | | 5 | `Evelyn (en)` | | 6 | `Celeste (en)` | | 7 | `Pippa (en)` | | 8 | `Tessa (en)` | | 9 | `Liam (en)` | | 10 | `Callum (en)` | | 11 | `Hamish (en)` | | 12 | `Abby (en)` | | 13 | `Graham (en)` | | 14 | `Rupert (en)` | | 15 | `Mortimer (en)` | | 16 | `Snik (en)` | | 17 | `Anjali (en)` | | 18 | `Saanvi (en)` | | 19 | `Arjun (en)` | | 20 | `Claire (en)` | | 21 | `Oliver (en)` | | 22 | `Simon (en)` | | 23 | `Elliot (en)` | | 24 | `James (en)` | | 25 | `Serena (en)` | | 26 | `Gareth (en)` | | 27 | `Vinny (en)` | | 28 | `Lauren (en)` | | 29 | `Jessica (en)` | | 30 | `Ethan (en)` | | 31 | `Tyler (en)` | | 32 | `Jason (en)` | | 33 | `Chloe (en)` | | 34 | `Veronica (en)` | | 35 | `Victoria (en)` | | 36 | `Miranda (en)` | | 37 | `Sebastian (en)` | | 38 | `Victor (en)` | | 39 | `Malcolm (en)` | | 40 | `Kayla (en)` | | 41 | `Nate (en)` | | 42 | `Jake (en)` | | 43 | `Brian (en)` | | 44 | `Amina (en)` | | 45 | `Kelsey (en)` | | 46 | `Derek (en)` | | 47 | `Grant (en)` | | 48 | `Evan (en)` | | 49 | `Alex (en)` | | 50 | `Ashley (en)` | | 51 | `Craig (en)` | | 52 | `Deborah (en)` | | 53 | `Dennis (en)` | | 54 | `Edward (en)` | | 55 | `Elizabeth (en)` | | 56 | `Hades (en)` | | 57 | `Julia (en)` | | 58 | `Pixie (en)` | | 59 | `Mark (en)` | | 60 | `Olivia (en)` | | 61 | `Priya (en)` | | 62 | `Ronald (en)` | | 63 | `Sarah (en)` | | 64 | `Shaun (en)` | | 65 | `Theodore (en)` | | 66 | `Timothy (en)` | | 67 | `Wendy (en)` | | 68 | `Dominus (en)` | | 69 | `Hana (en)` | | 70 | `Clive (en)` | | 71 | `Carter (en)` | | 72 | `Blake (en)` | | 73 | `Luna (en)` | | 74 | `Yichen (zh)` | | 75 | `Xiaoyin (zh)` | | 76 | `Xinyi (zh)` | | 77 | `Jing (zh)` | | 78 | `Erik (nl)` | | 79 | `Katrien (nl)` | | 80 | `Lennart (nl)` | | 81 | `Lore (nl)` | | 82 | `Alain (fr)` | | 83 | `Hélène (fr)` | | 84 | `Mathieu (fr)` | | 85 | `Étienne (fr)` | | 86 | `Johanna (de)` | | 87 | `Josef (de)` | | 88 | `Gianni (it)` | | 89 | `Orietta (it)` | | 90 | `Asuka (ja)` | | 91 | `Satoshi (ja)` | | 92 | `Hyunwoo (ko)` | | 93 | `Minji (ko)` | | 94 | `Seojun (ko)` | | 95 | `Yoona (ko)` | | 96 | `Szymon (pl)` | | 97 | `Wojciech (pl)` | | 98 | `Heitor (pt)` | | 99 | `Maitê (pt)` | | 100 | `Diego (es)` | | 101 | `Lupita (es)` | | 102 | `Miguel (es)` | | 103 | `Rafael (es)` | | 104 | `Svetlana (ru)` | | 105 | `Elena (ru)` | | 106 | `Dmitry (ru)` | | 107 | `Nikolai (ru)` | | 108 | `Riya (hi)` | | 109 | `Manoj (hi)` | | 110 | `Yael (he)` | | 111 | `Oren (he)` | | 112 | `Nour (ar)` | | 113 | `Omar (ar)` | ## OpenAPI ````yaml en/api-reference/audio-series/inworld/inworld-tts-1.5-max-generate.json POST /v1/predictions openapi: 3.1.0 info: title: Inworld TTS 1.5 Max version: 1.0.0 servers: - url: https://api.shuyou.ai security: - bearerAuth: [] paths: /v1/predictions: post: tags: - Audio Generation summary: Inworld TTS 1.5 Max description: >- Inworld TTS 1.5 Max (`inworld-tts-1.5-max`) converts text to speech asynchronously via POST /v1/predictions. Poll [Get a prediction](/en/api-reference/task-management/get-prediction) using `data.task_id`, or configure top-level `webhook` for completion callbacks. operationId: createInworldTts15MaxPrediction requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/InworldTts15MaxPredictionRequest' examples: text_to_speech: summary: Text to speech value: model: inworld-tts-1.5-max input: prompt: Welcome to ShuYou AI documentation. voice: Craig (en) webhook: https://api.shuyou.ai/backend/api/callback text_to_speech_minimal: summary: Minimal request value: model: inworld-tts-1.5-max input: prompt: Hello from Inworld TTS. responses: '200': description: Async task created content: application/json: schema: $ref: '#/components/schemas/PredictionTaskResponse' example: data: task_id: 2c4d50261173430290971a2395a3b607 task_status: processing '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '402': description: Insufficient quota content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '403': description: Model access denied content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: InworldTts15MaxPredictionRequest: type: object required: - model - input properties: model: type: string description: Model ID. Use `inworld-tts-1.5-max` for this endpoint. enum: - inworld-tts-1.5-max default: inworld-tts-1.5-max example: inworld-tts-1.5-max input: $ref: '#/components/schemas/InworldTts15MaxInput' webhook: type: string format: uri description: >- Optional HTTPS callback URL when the task completes, fails, or is cancelled. PredictionTaskResponse: type: object properties: data: type: object properties: task_id: type: string description: Async task ID. Use with Get a prediction or webhook correlation. example: 2c4d50261173430290971a2395a3b607 task_status: type: string description: Current task status, e.g. `processing`. example: processing required: - task_id - task_status required: - data ErrorResponse: type: object properties: error: type: object properties: code: type: string message: type: string type: type: string InworldTts15MaxInput: type: object required: - prompt properties: prompt: type: string maxLength: 2000 description: The text to synthesize into speech. Maximum 2000 characters. example: Welcome to ShuYou AI documentation. voice: type: string description: >- Voice preset for speech generation. Pass the value exactly as in the voice table on this page (113 presets). Default `Craig (en)`. default: Craig (en) example: Craig (en) additionalProperties: true securitySchemes: bearerAuth: type: http scheme: bearer description: '`Authorization: Bearer YOUR_API_KEY`' ````