FLW/VibeVoice
2
0
Fork 0
Code Activity

Cloning from Github

Browse Source
This commit is contained in:
Marco Olimpi
2025-10-20 18:58:25 +02:00
commit 9643e6494d
50 changed files with 9257 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
demo/text_examples/1p_abs.txt Normal file
View File

@@ -0,0 +1,3 @@
Speaker 1: Generating long-form, multi-speaker conversational audio like podcasts poses significant challenges for traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking. This report presents VibeVoice, a novel model designed to synthesize long-form speech with multiple speakers by employing the next-token diffusion framework, a unified method for modeling continuous data by autoregressively generating latent vectors via diffusion.
Speaker 1: A core component of our approach is the continuous speech tokenizers operating at an ultra-low frame rate of 7.5. This tokenizer effectively preserves audio fidelity while significantly boosting computational efficiency for processing long sequences. This enables VibeVoice to synthesize long-form speech for up to 90 minutes (in a 64K context window length) with up to 4 speakers, capturing the authentic conversational "vibe" and surpassing all known open-source and closed-source dialogue models (for example, Gemini 2.5 Pro Preview TTS). Code and checkpoint are available now.