{"data":{"id":"microsoft/mai-voice-2-flash","name":"Microsoft AI: MAI-Voice-2-Flash","created":1784822080,"description":"MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft AI for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24 kHz mono speech across 15...","architecture":{"tokenizer":"Other","instruct_type":null,"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"]},"endpoints":[{"name":"Azure | microsoft/mai-voice-2-flash-20260723","model_id":"microsoft/mai-voice-2-flash","model_name":"Microsoft AI: MAI-Voice-2-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":null,"uptime_last_5m":null,"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}]}}