Azure SpeechText-to-speech

MAI-Voice-2

JSON

MAI-Voice 2 TTS Beta streaming, http, websocket

01 Price

Azure Speech doesn't publish a per-unit price for this model.

02 Languages 15, 18 with regional variants

03 Features 2 of 8 listed

  • Emotion controlnot listed
  • Voice cloningnot listed
  • Voice designnot listed
  • SSML
  • Phoneme inputnot listed
  • Speed / prosody controlnot listed
  • Style control
  • Multi-speakernot listed

"Not listed" means the provider's data doesn't mention it, not that the model lacks it.

04 Voices 47 compatible, browse all

  • No sample published

    Klaus

    male / German (DE) +17

    de-DE-Klaus:MAI-Voice-2
  • No sample published

    Mia

    female / German (DE) +17

    de-DE-Mia:MAI-Voice-2
  • No sample published

    Isla

    female, australian / English (AU) +17

    en-AU-Isla:MAI-Voice-2
  • No sample published

    Ethan

    male, american / English (US) +17

    en-US-Ethan:MAI-Voice-2
  • No sample published

    Grant

    male, american / English (US)

    en-US-Grant:MAI-Voice-2
  • No sample published

    Harper

    female, american / English (US) +17

    en-US-Harper:MAI-Voice-2

05 Get this record

curl https://voicedex.dev/v1/providers/azure/models/MAI-Voice-2

Free, no key needed. Use model id MAI-Voice-2 with Azure Speech's own API. API reference.

Esc

↑↓ move↵ open