MAI-Transcribe 1.5

MAI-Voice-2

Microsoft high-fidelity expressive text-to-speech with multilingual MAI-Voice-2 prebuilt voices.

MAI-Voice-2.1

Microsoft expressive, high-fidelity text-to-speech for long-form narration, with 97 prebuilt voices across 23 languages.

MAI-Voice-2.1-Flash

Microsoft fast text-to-speech for assistants and interactive applications, with 97 prebuilt voices across 23 languages.

VibeVoice

Long-form text-to-speech with multi-speaker dialogue support and 9 voice presets across English, Chinese, and Hindi.

GPT-4o Mini Transcribe

OpenAI's efficient speech-to-text model with improved accuracy over Whisper

GPT-4o Mini Transcribe (2025-03-20)

Original release snapshot of GPT-4o Mini Transcribe