add VibeVoice-Realtime

2025-12-04 05:38:30 -08:00
parent e81395cf6d
commit fc83be5d92
39 changed files with 8190 additions and 6 deletions
@@ -0,0 +1,2 @@
+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. 
+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. 
@@ -0,0 +1 @@
+VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking. A core innovation of VibeVoice is its use of continuous speech tokenizers operating at an ultra-low frame rate of 7.5 Hz. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a next-token diffusion framework, leveraging a Large Language Model to understand textual context and dialogue flow, and a diffusion head to generate high-fidelity acoustic details. The model can synthesize speech up to 90 minutes long with up to 4 distinct speakers, surpassing the typical 1-2 speaker limits of many prior models.
				`@@ -0,0 +1 @@`
				VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking. A core innovation of VibeVoice is its use of continuous speech tokenizers operating at an ultra-low frame rate of 7.5 Hz. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a next-token diffusion framework, leveraging a Large Language Model to understand textual context and dialogue flow, and a diffusion head to generate high-fidelity acoustic details. The model can synthesize speech up to 90 minutes long with up to 4 distinct speakers, surpassing the typical 1-2 speaker limits of many prior models.