{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/mai-voice-2/","md":"https://postcutoff.com/m/mai-voice-2/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"mai-voice-2","name":"MAI-Voice-2 / MAI-Voice-2-Flash","org":"Microsoft","family":"MAI-Voice","released":"2026-06-02","status":"preview","type":"audio/speech","modality_in":["text"],"modality_out":["audio"],"open_weights":false,"model_license":"proprietary","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":{"per_million_characters":22,"per_million_characters_flash":15,"unit":"USD per 1M characters (MAI-Voice-2 / MAI-Voice-2-Flash, 'starting at')","source":"https://microsoft.ai/models/mai-voice-2/"},"price_line":"$22 per 1M characters","access":[{"provider":"Azure Speech in Microsoft Foundry (SSML voice name)","model_id":"en-US-Harper:MAI-Voice-2","endpoint":"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1","docs":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-voices"},{"provider":"Azure Speech in Microsoft Foundry (SSML voice name)","model_id":"en-US-Harper:MAI-Voice-2-Flash","docs":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-voices"},{"provider":"Azure Voice Live (TTS output)","model_id":"MAI-Voice-2-Flash","docs":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-how-to"},{"provider":"OpenRouter","model_id":"microsoft/mai-voice-2","endpoint":"https://openrouter.ai/api/v1/audio/speech"},{"provider":"OpenRouter","model_id":"microsoft/mai-voice-2-flash"},{"provider":"Web app (MAI Playground)","url":"https://playground.microsoft.ai/"}],"capabilities":[{"name":"Gated instant voice cloning","detail":"Matches a consented reference voice from a 5-60 s clip without training; only approved (Limited Access) licensed voices can be synthesized.","first":false,"discovered":"launch","source":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-voices"},{"name":"SSML emotion/style control","detail":"mstts:express-as styles (angry, fearful, joyful, whispering, shouting, etc.) with styledegree, across 15 languages / 18 locales.","first":false,"discovered":"launch","source":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-voices"},{"name":"Low-latency Flash tier","detail":"MAI-Voice-2-Flash (public preview from 2026-07-23) targets voice agents/IVR; Microsoft quotes ~225 ms latency vs ~1 s for MAI-Voice-2 (for a 45 s clip).","first":false,"discovered":"later","source":"https://microsoft.ai/models/mai-voice-2/"}],"entry":"2026-06-02-microsoft-mai-models-build-2026","notes":"Launched at Build 2026-06-02 (MAI-Voice-2); Flash followed 2026-07-23 (date per secondary sources). Both public preview in Azure Speech. Languages include en-US/AU, de, fr, es-ES/MX, pt-BR/PT, it, ko, zh-CN, tr, ru, th, nl, ro, hu, hi. Also used in Copilot (Audio Expressions). Predecessor MAI-Voice-1 no longer listed on the MAI-Voice docs page. Also on Fireworks and Baseten (ids not verified).","verified":"2026-09-29","body_md":"Microsoft's in-house expressive TTS, used through standard Azure Speech SSML.\n\n```bash\ncurl -X POST \"https://$REGION.tts.speech.microsoft.com/cognitiveservices/v1\" \\\n  -H \"Ocp-Apim-Subscription-Key: $SPEECH_KEY\" -H \"Content-Type: application/ssml+xml\" \\\n  -H \"X-Microsoft-OutputFormat: audio-24khz-160kbitrate-mono-mp3\" \\\n  --data '<speak version=\"1.0\" xml:lang=\"en-US\"><voice name=\"en-US-Harper:MAI-Voice-2\">Hello from MAI Voice.</voice></speak>' -o out.mp3\n```\n\nSources: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-voices · https://microsoft.ai/models/mai-voice-2/ · https://microsoft.ai/news/building-a-hillclimbing-machine-launching-seven-new-mai-models/","page_url":"https://postcutoff.com/m/mai-voice-2/","standing":{"kind":"speech and audio","newer_count":54,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"vibevoice","name":"VibeVoice (ASR, ASR-Streaming, ASR-BitNet, Realtime-0.5B TTS)","org":"Microsoft","released":"2025-08-25","page_url":"https://postcutoff.com/m/vibevoice/"},"after":{"id":"mai-transcribe-2","name":"MAI-Transcribe-2","org":"Microsoft","released":"2026-09-03","page_url":"https://postcutoff.com/m/mai-transcribe-2/"},"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}