← PROJECTS

MAI Speech TRIAL

MAI Speech offers callable low-latency streaming transcription and synthesis with published pricing; multilingual quality and interruption recovery on real calls still need independent validation.

Next stepIn one day, test mixed Chinese-English calls for first-token latency, error rate, interruption recovery, naturalness and per-turn cost.

Judgment reviewed 2026-10-04 · Basis: Microsoft releases streaming speech models with 100 ms partials

RSS

Availability & adoption

availability
Microsoft Foundry and public playgrounds; voice also on OpenRouter; LiveKit announced

Timeline