Projects

Open-Source Frontier Voice AI — VibeVoice-ASR supports single-pass processing for up to 60 minutes of audio, unifying ASR, Speaker Diarization, and Timestamping. 50+ languages supported.

Habibi — The first open-source unified-dialectal Arabic TTS framework covering 12+ regional dialects. Competitive with ElevenLabs Eleven v3 (alpha).