{"data":{"id":"microsoft/mai-voice-2.1-flash","name":"Microsoft AI: MAI-Voice-2.1-Flash","created":1790870485,"description":"MAI-Voice-2.1-Flash is a low-latency text-to-speech model from Microsoft AI, optimized for real-time responsiveness. It produces natural, expressive speech across 23 languages, with human-like intonation, rhythm, and emotional nuance. It is...","architecture":{"tokenizer":"Other","instruct_type":null,"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"]},"endpoints":[{"name":"Azure | microsoft/mai-voice-2.1-flash-20261001","model_id":"microsoft/mai-voice-2.1-flash","model_name":"Microsoft AI: MAI-Voice-2.1-Flash","context_length":0,"pricing":{"prompt":"0.000015","completion":"0","discount":0},"provider_name":"Azure","tag":"azure","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":99.56896551724138,"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}]}}