microsoft logo
microsoft

Microsoft AI: MAI-Voice-2.1

Opis źródłowy (angielski)

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...

Przegląd

Specyfikacja modelu

Kontekst
Brak danych
Maksymalne wyjście
Brak danych
Architektura
text->speech
Tokenizer
Other
Granica wiedzy
Brak danych
Moderowany
Nie
OPENROUTER

Pełny cennik

Stawki zsynchronizowane z OpenRouter, za milion tokenów.

Znaki
$22
za milion znaków
API

Konfiguracja modelu

Obsługiwane głosy

cs-CZ-Grant:MAI-Voice-2.1cs-CZ-Harper:MAI-Voice-2.1da-DK-Grant:MAI-Voice-2.1da-DK-Harper:MAI-Voice-2.1de-DE-Grant:MAI-Voice-2.1de-DE-Harper:MAI-Voice-2.1de-DE-Klaus:MAI-Voice-2.1de-DE-Mia:MAI-Voice-2.1en-AU-Isla:MAI-Voice-2.1en-GB-Emily:MAI-Voice-2.1en-GB-Harry:MAI-Voice-2.1en-IN-Dhruv:MAI-Voice-2.1en-IN-Priya:MAI-Voice-2.1en-US-Ethan:MAI-Voice-2.1en-US-Grant:MAI-Voice-2.1en-US-Harper:MAI-Voice-2.1en-US-Iris:MAI-Voice-2.1en-US-Jasper:MAI-Voice-2.1en-US-Olivia:MAI-Voice-2.1en-US-Sage:MAI-Voice-2.1es-ES-Marta:MAI-Voice-2.1es-MX-Alejo:MAI-Voice-2.1es-MX-Grant:MAI-Voice-2.1es-MX-Harper:MAI-Voice-2.1es-MX-Valeria:MAI-Voice-2.1fi-FI-Grant:MAI-Voice-2.1fi-FI-Harper:MAI-Voice-2.1fr-FR-Grant:MAI-Voice-2.1fr-FR-Harper:MAI-Voice-2.1fr-FR-Marc:MAI-Voice-2.1fr-FR-Soleil:MAI-Voice-2.1hi-IN-Arjun:MAI-Voice-2.1hi-IN-Dhruv:MAI-Voice-2.1hi-IN-Grant:MAI-Voice-2.1hi-IN-Harper:MAI-Voice-2.1hi-IN-Kavya:MAI-Voice-2.1hi-IN-Priya:MAI-Voice-2.1hu-HU-Bence:MAI-Voice-2.1hu-HU-Grant:MAI-Voice-2.1hu-HU-Harper:MAI-Voice-2.1hu-HU-Levente:MAI-Voice-2.1hu-HU-Lilla:MAI-Voice-2.1hu-HU-Reka:MAI-Voice-2.1id-ID-Grant:MAI-Voice-2.1id-ID-Harper:MAI-Voice-2.1it-IT-Grant:MAI-Voice-2.1it-IT-Harper:MAI-Voice-2.1it-IT-Luca:MAI-Voice-2.1it-IT-Rosa:MAI-Voice-2.1ko-KR-Grant:MAI-Voice-2.1ko-KR-Haena:MAI-Voice-2.1ko-KR-Harper:MAI-Voice-2.1ko-KR-Junho:MAI-Voice-2.1nb-NO-Grant:MAI-Voice-2.1nb-NO-Harper:MAI-Voice-2.1nl-NL-Grant:MAI-Voice-2.1nl-NL-Harper:MAI-Voice-2.1nl-NL-Sander:MAI-Voice-2.1pl-PL-Grant:MAI-Voice-2.1pl-PL-Harper:MAI-Voice-2.1pt-BR-Caio:MAI-Voice-2.1pt-BR-Grant:MAI-Voice-2.1pt-BR-Harper:MAI-Voice-2.1pt-BR-Luana:MAI-Voice-2.1pt-BR-Pedro:MAI-Voice-2.1pt-BR-Rafael:MAI-Voice-2.1pt-PT-Grant:MAI-Voice-2.1pt-PT-Harper:MAI-Voice-2.1pt-PT-Rui:MAI-Voice-2.1ro-RO-Andrei:MAI-Voice-2.1ro-RO-Elena:MAI-Voice-2.1ro-RO-Grant:MAI-Voice-2.1ro-RO-Harper:MAI-Voice-2.1ro-RO-Ioana:MAI-Voice-2.1ro-RO-Radu:MAI-Voice-2.1ru-RU-Grant:MAI-Voice-2.1ru-RU-Harper:MAI-Voice-2.1ru-RU-Lev:MAI-Voice-2.1ru-RU-Masha:MAI-Voice-2.1sv-SE-Grant:MAI-Voice-2.1sv-SE-Harper:MAI-Voice-2.1th-TH-Grant:MAI-Voice-2.1th-TH-Harper:MAI-Voice-2.1th-TH-Krit:MAI-Voice-2.1th-TH-Nattapong:MAI-Voice-2.1tr-TR-Aydin:MAI-Voice-2.1tr-TR-Elif:MAI-Voice-2.1tr-TR-Grant:MAI-Voice-2.1tr-TR-Harper:MAI-Voice-2.1vi-VN-Grant:MAI-Voice-2.1vi-VN-Harper:MAI-Voice-2.1zh-CN-Bo:MAI-Voice-2.1zh-CN-Grant:MAI-Voice-2.1zh-CN-Harper:MAI-Voice-2.1zh-CN-Lan:MAI-Voice-2.1zh-CN-Mei:MAI-Voice-2.1zh-CN-Wei:MAI-Voice-2.1
API

Szybki start

Ustaw lokalnie OPENROUTER_API_KEY. Python wymaga requests, a JavaScript działa w Node.js. Klucz przechowuj na serwerze.

Wybierz obsługiwany głos. Zastąp YOUR_VOICE_ID, jeśli nie podano głosu.

Dokumentacja API

curl --fail-with-body https://openrouter.ai/api/v1/audio/speech \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"microsoft/mai-voice-2.1","input":"Hello!","voice":"cs-CZ-Grant:MAI-Voice-2.1","response_format":"mp3"}' \
  --output speech.mp3
Możliwości i modalności

Wejście → Wyjście

Wejście
text
Wyjście
speech
API

Obsługiwane parametry API

Dostępni dostawcy

1 Dostawca

Sprawdzono: 2 października 2026

Dostawcy na żywo w OpenRouter

Dostępność, opóźnienie, przepustowość i routing stale się zmieniają. Aktualne dane są na stronie źródłowej.

OpenRouter

Azure

Brak danych
Kontekst
Brak danych
Maksymalne wyjście
Brak danych
microsoft

4 modele

Wszystkie modele
microsoft logomicrosoft

Microsoft: Microsoft-Decision-1

Microsoft-Decision-1 is a small model built for fast decision-making. Instead of generating text, it reads the provided content and returns a calibrated probability for each fixed answer option, so the...

Kontekst
33K
Wejście
text
Wyjście
decisions
Wejście: $0.042 za milion tokenówWyjście: Bezpłatnie za milion tokenów
Zobacz szczegóły modelu →
microsoft logomicrosoft

Microsoft AI: MAI-Voice-2.1-Flash

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...

Kontekst
Brak danych
Wejście
text
Wyjście
speech
Znaki: $15 za milion znaków
Zobacz szczegóły modelu →
microsoft logomicrosoft

Microsoft AI: MAI-Image-2.6

MAI-Image-2.6 is an image generation and editing model from Microsoft AI, the precision tier of the MAI-Image-2.6 family alongside the faster MAI-Image-2.6 Flash. It is suited for design-ready visuals and...

Kontekst
4K
Wejście
text · image
Wyjście
image
Wejście: $5 za milion tokenówObraz wyjściowy: $38 za milion tokenów
Zobacz szczegóły modelu →
microsoft logomicrosoft

Microsoft AI: MAI-Image-2.6 Flash

MAI-Image-2.6 Flash is the lower-latency, lower-cost member of the MAI-Image-2.6 family from Microsoft AI, built for latency-sensitive, high-throughput production image generation and editing at comparable quality to the precision tier....

Kontekst
4K
Wejście
text · image
Wyjście
image
Wejście: $1.75 za milion tokenówObraz wyjściowy: $19 za milion tokenów
Zobacz szczegóły modelu →