> ## Documentation Index > Fetch the complete documentation index at: https://docs.modellix.ai/llms.txt > Use this file to discover all available pages before exploring further. # CosyVoice V3 Plus > [Core Function] CosyVoice v3 Plus is Alibaba's high-quality text-to-speech model. [Strengths] System voices (e.g. longanyang, longanhuan), SSML and LaTeX input, hot_fix pronunciation correction, AIGC watermark, and output in mp3, pcm, wav, or opus. System-voice instruction must use the fixed Chinese formats in the CosyVoice voice list. [Best For] Brand voiceovers, audiobooks, high-quality narration, marketing clips, and scenarios where speech quality matters more than minimum latency. [Limitations] Do NOT use for real-time streaming or word-level timestamps. Fewer system voices than Flash. [Routing] Choose Plus when quality or narration fidelity matters most. Choose cosyvoice-v3-flash for lower latency or a richer system-voice catalog. ## OpenAPI ````yaml /media-model-api/alibaba/alibaba-t2s.json post /alibaba/cosyvoice-v3-plus openapi: 3.1.0 info: title: Alibaba CosyVoice and Qwen-Audio Text-to-Speech Models API description: >- CosyVoice and Qwen-Audio text-to-speech on Alibaba: system-voice CosyVoice v3 Plus/Flash, Qwen-Audio 3.0 TTS Plus/Flash, plus one-shot voice design (cosyvoice-design). Submit an async task, then poll GET /api/v1/tasks/{task_id} for the audio. For system voices, see the Alibaba CosyVoice and Qwen-Audio-TTS voice lists. version: 1.0.0 contact: name: Modellix Support email: support@modellix.ai servers: - url: https://api.modellix.ai/api/v1 description: >- The text-to-speech models API from Alibaba (CosyVoice v3, Qwen-Audio 3.0 TTS, and cosyvoice-design). security: - bearerAuth: [] paths: /alibaba/cosyvoice-v3-plus: post: summary: CosyVoice V3 Plus description: >- [Core Function] CosyVoice v3 Plus is Alibaba's high-quality text-to-speech model. [Strengths] System voices (e.g. longanyang, longanhuan), SSML and LaTeX input, hot_fix pronunciation correction, AIGC watermark, and output in mp3, pcm, wav, or opus. System-voice instruction must use the fixed Chinese formats in the CosyVoice voice list. [Best For] Brand voiceovers, audiobooks, high-quality narration, marketing clips, and scenarios where speech quality matters more than minimum latency. [Limitations] Do NOT use for real-time streaming or word-level timestamps. Fewer system voices than Flash. [Routing] Choose Plus when quality or narration fidelity matters most. Choose cosyvoice-v3-flash for lower latency or a richer system-voice catalog. operationId: cosyvoice3PlusAsync requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CosyVoice3PlusTTSRequest' examples: basic: summary: Minimal synthesis with system voice value: text: There is a large garden behind my house. voice: longanyang with_controls: summary: System voice with format and prosody value: text: How is the weather today? voice: longanhuan format: wav sample_rate: 24000 volume: 50 rate: 1 pitch: 1 language_hint: en responses: '200': description: >- Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; synthesized audio is returned on the task result. content: application/json: schema: $ref: '#/components/schemas/AsyncTaskResponse' example: code: 0 message: success data: status: pending task_id: task-cosyvoice-v3-plus-001 model_id: alibaba/cosyvoice-v3-plus get_result: method: GET url: >- https://api.modellix.ai/api/v1/tasks/task-cosyvoice-v3-plus-001 '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: CosyVoice3PlusTTSRequest: allOf: - $ref: '#/components/schemas/CosyVoice3TTSRequestBase' - type: object required: - text - voice properties: voice: type: string description: >- System voice for cosyvoice-v3-plus. Complete set from the Alibaba CosyVoice voice list (https://help.aliyun.com/zh/model-studio/cosyvoice-voice-list). enum: - longanyang - longanhuan example: longanyang AsyncTaskResponse: description: Response object for asynchronous task submission. type: object required: - code - message - data properties: code: type: integer description: Response code, 0 indicates success example: 0 message: type: string description: Response message example: success data: type: object required: - status - task_id - model_id description: >- Task submission details. Poll GET /api/v1/tasks/{task_id} until status is success; audio appears in result.resources. properties: status: type: string enum: - pending - processing description: Initial task status example: pending task_id: type: string description: Unique task identifier for polling example: task-cosyvoice-v3-plus-001 model_id: type: string description: Model ID in provider/model format example: alibaba/cosyvoice-v3-plus get_result: type: object description: >- Endpoint to query the task result. See Common API: Query Task Result. properties: method: type: string example: GET url: type: string example: >- https://api.modellix.ai/api/v1/tasks/task-cosyvoice-v3-plus-001 CosyVoice3TTSRequestBase: type: object description: >- Shared CosyVoice v3 TTS request fields. Submit as an async task; poll GET /api/v1/tasks/{task_id} for the audio URL in result.resources. properties: text: type: string description: >- Text to synthesize. Required. Max 20,000 Unicode characters. Supports plain text, SSML (set enable_ssml to true), and LaTeX formulas per Alibaba documentation. minLength: 1 maxLength: 20000 example: There is a large garden behind my house. format: type: string description: Audio encoding format. Default mp3. enum: - mp3 - pcm - wav - opus default: mp3 example: mp3 sample_rate: type: integer description: Audio sample rate in Hz. Default 22050. enum: - 8000 - 16000 - 22050 - 24000 - 44100 - 48000 default: 22050 example: 24000 volume: type: integer description: Output volume. Default 50. Range 0 (silent) to 100 (maximum). minimum: 0 maximum: 100 default: 50 example: 50 rate: type: number description: Speech rate multiplier. Default 1.0. Range 0.5 (slow) to 2.0 (fast). minimum: 0.5 maximum: 2 default: 1 example: 1 pitch: type: number description: Pitch multiplier. Default 1.0. Range 0.5 (lower) to 2.0 (higher). minimum: 0.5 maximum: 2 default: 1 example: 1 bit_rate: type: integer description: >- Audio bit rate in kbps. Optional. Range 6 to 510. Only supported when format is opus; do not use for mp3, pcm, or wav. minimum: 6 maximum: 510 example: 32 instruction: type: string description: >- Optional speaking-style instruction for Instruct-capable system voices. Enforced weighted length ≤100 (CJK ideographs / Han count as 2; other characters count as 1). Alibaba requires fixed Chinese formats from the CosyVoice voice list for system voices. example: Speak in a friendly customer-service tone. language_hint: type: string description: >- Target language hint for pronunciation (numbers, symbols, minor languages). enum: - zh - en - fr - de - ja - ko - ru - pt - th - id - vi - es - it - ms - fil - ar example: en seed: type: integer description: >- Random seed for reproducible synthesis when text, voice, and other parameters are identical. Default 0. Range 0 to 65535. minimum: 0 maximum: 65535 default: 0 example: 0 enable_ssml: type: boolean description: >- Whether to parse text as SSML. Default false. When true, text must follow Alibaba CosyVoice SSML rules. default: false example: false hot_fix: type: object description: >- Text hot-fix before synthesis. Optional object with pronunciation (custom pinyin for Chinese words) and replace (text substitution) arrays per Alibaba HTTP API. example: replace: - Modellix: Modelix enable_aigc_tag: type: boolean default: false description: >- Embed AIGC invisible watermark into wav/mp3/opus output. Supported on cosyvoice-v3-plus and cosyvoice-v3-flash. aigc_propagator: type: string description: AIGC ContentPropagator. Only effective when enable_aigc_tag is true. aigc_propagate_id: type: string description: AIGC PropagateID. Only effective when enable_aigc_tag is true. ErrorResponse: type: object required: - code - message properties: code: type: integer description: Error code (equals HTTP status code) example: 400 message: type: string description: 'Error message in format ''Category: detail''' example: 'Invalid parameters: voice is required for alibaba/cosyvoice-v3-plus' responses: BadRequest: description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 400 message: >- Invalid parameters: voice is required for alibaba/cosyvoice-v3-plus Unauthorized: description: Unauthorized - Invalid or missing API Key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 401 message: 'Authentication failed: invalid API key' TooManyRequests: description: Too many requests - Rate limit exceeded headers: X-RateLimit-Limit: description: Maximum requests per minute schema: type: integer example: 100 X-RateLimit-Remaining: description: Remaining quota in current window schema: type: integer example: 0 X-RateLimit-Reset: description: Rate limit window reset time (Unix timestamp) schema: type: integer example: 1704067260 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 429 message: >- Rate limit exceeded: 100 requests per minute, retry after 60 seconds InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 500 message: Internal server error securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'Modellix API Key. Format: Bearer ' ````