← All models
Microsoft: MAI-Voice-2.1
microsoft/mai-voice-2.1speech
MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and speaker consistency over long-form content. It is suited for audiobooks, podcasts, lectures, narration, and brand audio where maximum voice quality matters. The model prioritizes naturalness and expressivity over latency-critical generation.
In the API, set voice to a full voice ID with the model suffix, such as "en-US-Harper:MAI-Voice-2.1". A voice's locale sets the synthesis language. Set response_format to "mp3" or "pcm" (24 kHz mono). Harper and Grant support the agent, customer-call-center, educational, and narrator speaking styles, and many locale voices add emotion styles such as excited, happy, sad, and whispering. The full list of voices is in the supported_voices field of the models API.
Price
Released
Oct 1, 2026
Parameters
inputrequiredvoiceru-RU-Masha:MAI-Voice-2.1 · ru-RU-Lev:MAI-Voice-2.1 · ru-RU-Grant:MAI-Voice-2.1 · ru-RU-Harper:MAI-Voice-2.1 · en-US-Harper:MAI-Voice-2.1 · en-US-Grant:MAI-Voice-2.1 · en-US-Ethan:MAI-Voice-2.1 · en-US-Iris:MAI-Voice-2.1 · en-US-Jasper:MAI-Voice-2.1 · en-US-Olivia:MAI-Voice-2.1 · en-US-Sage:MAI-Voice-2.1Voice sample· Sample voice: ru-RU-Masha
0:00 / 0:00
How to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
resp = client.audio.speech.create(
model="microsoft/mai-voice-2.1",
voice="ru-RU-Masha:MAI-Voice-2.1", # ru-RU-Masha:MAI-Voice-2.1, ru-RU-Lev:MAI-Voice-2.1, ru-RU-Grant:MAI-Voice-2.1, ru-RU-Harper:MAI-Voice-2.1, en-US-Harper:MAI-Voice-2.1...
input="Привет! Это Mixen AI.",
)
resp.stream_to_file("speech.mp3")
