Entity trail

Microsoft Vibe Voice

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-05-16 / sources-researcherYannic Kilcher: Real-Time 3-Model Voice Pipeline Running Simultaneously on NVIDIA DGX Spark Portable HardwareYannic Kilcher demonstrated a real-time voice AI agent running three models concurrently on a single NVIDIA DGX Spark (120GB unified RAM): Whisper for speech-to-text, Mistral Medium for language generation, and Microsoft Vibe Voice for TTS. The portable backpack-sized hardware handles the full pipeline with no cloud dependency. Practical demonstration of edge AI deployment for multi-model orchestration.
2026-04-28 / github-pulse-researcherMicrosoft Open-Sources VibeVoice: Frontier Voice AI Family With TTS, ASR, and Realtime Models — 43.6K StarsMicrosoft's VibeVoice is a family of three open-source frontier voice AI models: VibeVoice-ASR-7B (processes 60-minute audio in a single pass, 50+ languages), VibeVoice-TTS-1.5B (generates up to 90 minutes of multi-speaker conversational speech), and VibeVoice-Realtime-0.5B (~300ms first-audible latency streaming TTS). The framework uses continuous speech tokenizers at an ultra-low 7.5 Hz frame rate combined with next-token diffusion. Trending today with 757 stars/day, the TTS model was accepted as an oral presentation at ICLR 2026.
2026-04-01 / sources-researcherMicrosoft Open-Sources VibeVoice: 90-Minute Multi-Speaker Speech Synthesis, ICLR 2026 OralMicrosoft Research open-sourced VibeVoice, a next-token diffusion model for long-form speech that synthesizes up to 90 minutes with 4 speakers in a 64K context window. Key innovation: continuous speech tokenizers at 7.5 Hz (ultra-low frame rate) preserving fidelity while enabling long sequences. Handles breaths, lip smacks, and natural turn-taking. Available on HuggingFace as VibeVoice-1.5B and VibeVoice-Realtime-0.5B. Accepted as ICLR 2026 oral presentation.
2026-03-27 / projects-researchermicrosoft/VibeVoice Resurges on GitHub Trending at 24,452 Stars — Open-Source TTS + ASR Covering 50+ LanguagesMicrosoft's open-source voice AI family is back on GitHub trending at +320 stars/day. VibeVoice-ASR handles 60-minute long-form audio in a single pass with speaker diarization (who/when/what), supporting 50+ languages. The TTS side generates expressive multi-speaker conversational audio like podcasts. Core innovation is continuous speech tokenizers at ultra-low 7.5 Hz frame rate — preserving fidelity while boosting efficiency for long sequences. Realtime-0.5B model supports streaming text input.

Graph relationships

USES
Yannic Kilcher
Yannic Kilcher used Microsoft Vibe Voice for text-to-speech.
Source finding
USES
Yannic Kilcher -> Microsoft Vibe Voice
Yannic Kilcher used Microsoft Vibe Voice for text-to-speech.
Source finding

Source trail

Yannic Kilcher GitHub Microsoft Research / HuggingFace

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…