{"data":{"id":"fish-audio/s2.1-pro","name":"Fish Audio: S2.1 Pro","created":1785353732,"description":"S2.1 Pro is a production-oriented text-to-speech model from Fish Audio. It is suited for multilingual voice applications, expressive narration, and dialogue synthesis, with open-ended natural-language controls for speaking style and...","architecture":{"tokenizer":"Other","instruct_type":null,"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"]},"endpoints":[{"name":"Fish Audio | fish-audio/s2.1-pro-20260729","model_id":"fish-audio/s2.1-pro","model_name":"Fish Audio: S2.1 Pro","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":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"native_tools":{},"supports_voice_cloning":true,"supports_multiple_audio_references":false,"supports_image_reference":false,"supports_diarization":false,"latency_last_30m":null,"throughput_last_30m":null}]}}