{"data":{"id":"fish-audio/transcribe-1","name":"Fish Audio: Transcribe 1","created":1785353735,"description":"Transcribe 1 is a speech-to-text model from Fish Audio. It is suited for audio transcription with automatic language detection and can return timestamped word-level segments when alignment details are requested.","architecture":{"tokenizer":"Other","instruct_type":null,"modality":"audio->transcription","input_modalities":["audio"],"output_modalities":["transcription"]},"endpoints":[{"name":"Fish Audio | fish-audio/transcribe-1-20260729","model_id":"fish-audio/transcribe-1","model_name":"Fish Audio: Transcribe 1","context_length":0,"pricing":{"prompt":"0.0001","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":false,"supports_multiple_audio_references":false,"supports_image_reference":false,"supports_diarization":false,"latency_last_30m":null,"throughput_last_30m":null}]}}