{"info":{"title":"ModelRunner OpenAPI schema for resemble-ai/chatterboxhd/text-to-speech","version":"0.1.0"},"paths":{"/health-check":{"get":{"summary":"Healthcheck","responses":{"200":{"content":{"application/json":{"schema":{"title":"Response Healthcheck Health Check Get"}}},"description":"Successful Response"}},"operationId":"healthcheck_health_check_get"}}},"openapi":"3.1.0","components":{"schemas":{"Input":{"type":"object","title":"Input","required":["text"],"properties":{"cfg":{"type":"number","title":"Cfg","default":0.5,"maximum":1,"minimum":0,"x-order":4,"description":"Classifier-free guidance weight controlling the conditioning factor. For expressive or dramatic speech, try lower values (e.g. ~0.3) and increase exaggeration to around 0.7 or higher. If the reference speaker has a fast speaking style, lowering cfg to around 0.3 can improve pacing."},"seed":{"type":"integer","title":"Seed","default":0,"minimum":0,"x-order":6,"description":"Random seed for reproducibility. Set a fixed integer to repeat a generation; 0 uses a random seed."},"text":{"type":"string","title":"Text","x-order":0,"description":"The text to synthesize into speech."},"voice":{"allOf":[{"$ref":"#/components/schemas/VoiceEnum"}],"title":"Voice","default":"Aurora","x-order":1,"description":"The named voice to speak the text. If a reference clip is provided in audio_url it overrides this setting; if both are left unset a random voice is used."},"audio_url":{"type":"string","title":"Audio Url","format":"uri","x-order":2,"description":"Optional reference recording for zero-shot voice cloning. Provide a clean, single-speaker clip to clone that voice; it overrides the voice selection. Leave unset to use the named voice."},"temperature":{"type":"number","title":"Temperature","default":0.8,"maximum":5,"minimum":0.05,"x-order":7,"description":"Sampling temperature controlling the randomness of generation. Lower is steadier and more predictable; higher adds variation to prosody and delivery."},"exaggeration":{"type":"number","title":"Exaggeration","default":0.5,"maximum":2,"minimum":0.25,"x-order":3,"description":"Emotion and intensity exaggeration. Higher values produce more dramatic, expressive delivery; lower values are calmer and more measured."},"high_quality_audio":{"type":"boolean","title":"High Quality Audio","default":false,"x-order":5,"description":"When true, the generated audio is upscaled to 48kHz for higher quality at the cost of longer generation time. When false, the audio is 24kHz."}},"x-fal-order-properties":["text","voice","audio_url","exaggeration","cfg","high_quality_audio","seed","temperature"]},"Output":{"type":"string","title":"Output","format":"uri","description":"Generated speech audio file URL (WAV)."},"VoiceEnum":{"enum":["Aurora","Blade","Britney","Carl","Cliff","Richard","Rico","Siobhan","Vicky"],"type":"string","title":"VoiceEnum"}}}}