{"synthesize":{"path":"/speech/synthesize","method":"POST","kind":"inference","tier":"exclusive","description":"Synthesize speech from text on the qwen-audio-3.0-tts-plus model. Billed on the Exclusive tier, per clip. Returns an audio_id immediately; poll /speech/status/{audio_id} then download /speech/audio/{audio_id} (both free).","parameters":{"text":{"type":"string","description":"Text to speak, up to 4,000 characters. Mixed Chinese (Mandarin) and English supported"},"voice":{"type":"string","description":"Voice. longanlufeng = male (bright, cheerful); longanlingxin = female (warm, empathetic). Default longanlufeng","enum":["longanlufeng","longanlingxin"],"default":"longanlufeng"},"format":{"type":"string","description":"Audio container/codec. Default mp3","enum":["mp3","wav","pcm","opus"],"default":"mp3"},"sample_rate":{"type":"integer","description":"Sample rate in Hz: 8000, 16000, 22050, 24000, 44100 or 48000. Empty = format default (22050)","enum":[8000,16000,22050,24000,44100,48000]},"volume":{"type":"integer","description":"Volume 0-100. Default 50"},"rate":{"type":"number","description":"Speech rate multiplier 0.5-2.0. Default 1.0"},"pitch":{"type":"number","description":"Pitch multiplier 0.5-2.0. Default 1.0"}},"required":["text"],"output_example":{"audio_id":"welcome-to-the-x4-3f9a1c","status":"synthesizing","model":"qwen-audio-3.0-tts-plus","voice":"longanlufeng","estimated_time_seconds":10},"latency_class":"async"}}