Qwen3-TTS Voice Design API Service: Qwen3-TTS Voice Design HTTP Service with Queue Control Concurrency Limit: 1 Queue Management: Enabled Response Format: JSON with download URL CORS: Enabled API Endpoints: POST /tts - Text to Speech (returns JSON) GET /download/ - Download generated audio file GET /health - Health check GET /queue/status - Queue status monitoring GET /docs - Swagger API documentation GET /redoc - ReDoc API documentation Request Parameters (POST /tts): Required: - text : Text to synthesize (1-5000 characters) Optional: - instruct : Voice design instruction (e.g., "Speak with an angry tone") - language : Language (default: Chinese) - Chinese : Chinese - English : English - Japanese : Japanese - Korean : Korean - Auto : Auto detect Response Format (POST /tts): Success Response: { "success": true, "message": "TTS generation completed", "data": { "request_id": "tts_123_20260316_120000", "download_url": "http://YOUR_SERVER:8000/download/tts_123_20260316_120000.wav", "filename": "tts_123_20260316_120000.wav", "processing_time": 2.35, "sample_rate": 12000, "text_preview": "Hello, this is a...", "language": "English" } } Technical Specifications: - Model Version : Qwen3-TTS-12Hz-1.7B-VoiceDesign - Sample Rate : 12000 Hz - Audio Format : WAV - Concurrency Mode : Async Queue - Concurrency Limit : 1 - Response Format : JSON - Audio Storage : Temporary files with download URLs - CORS : Enabled Important Notes: 1. API returns JSON response with download URL 2. Audio files are stored temporarily and available for download 3. Download URL format: https://voice.dzai.cc/download/ 4. Concurrency controlled by 'concurrency_number' parameter 5. CORS enabled for cross-origin requests Powered by Qwen3-TTS | Version 2.0.0 (Queue Control + JSON + CORS)