{"data":{"id":"fish-audio/s1","name":"Fish Audio: S1","created":1785353734,"description":"S1 is a multilingual text-to-speech model from Fish Audio. It is suited for voice applications that need broad emotional expression, using parenthetical controls to guide speaking style across its supported...","architecture":{"tokenizer":"Other","instruct_type":null,"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"]},"endpoints":[{"name":"Fish Audio | fish-audio/s1-20260729","model_id":"fish-audio/s1","model_name":"Fish Audio: S1","context_length":0,"pricing":{"prompt":"0.000015","completion":"0","discount":0},"provider_name":"Fish Audio","tag":"fish-audio","service_tier":null,"quantization":"unknown","max_completion_tokens":0,"max_prompt_tokens":null,"supported_parameters":[],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"native_tools":{},"supports_voice_cloning":false,"supports_multiple_audio_references":false,"supports_image_reference":false,"supports_diarization":false,"latency_last_30m":null,"throughput_last_30m":null}]}}