https://github.com/nari-labs/dia

A TTS model capable of generating ultra-realistic dialogue in one pass.
https://github.com/nari-labs/dia

ai open-weight text-to-speech

Last synced: about 1 year ago
JSON representation

A TTS model capable of generating ultra-realistic dialogue in one pass.

• Host: GitHub
• URL: https://github.com/nari-labs/dia
• Owner: nari-labs
• License: apache-2.0
• Created: 2025-04-19T07:15:57.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-04-21T17:37:38.000Z (about 1 year ago)
• Last Synced: 2025-04-21T17:41:31.740Z (about 1 year ago)
• Topics: ai, open-weight, text-to-speech
• Language: Python
• Homepage:
• Size: 611 KB
• Stars: 37
• Watchers: 2
• Forks: 1
• Open Issues: 0

Awesome Lists containing this project

• StarryDivineSky - nari-labs/dia - labs/dia是一个文本转语音（TTS）模型，其主要特色在于能够一次性生成超逼真的对话。该项目旨在实现高度自然流畅的语音合成效果，尤其擅长模拟对话场景中的语音特征。具体工作原理可能涉及先进的深度学习技术，例如Transformer架构或变分自编码器（VAE），以捕捉语音的细微变化和上下文依赖关系。通过训练大量对话数据，dia模型能够学习不同说话人的语音风格和情感表达，从而生成更具表现力和真实感的语音。该项目对于语音合成、人机交互、以及虚拟助手等领域具有潜在的应用价值，可以用于创建更自然、更具吸引力的语音交互体验。 (语音合成 / 资源传输下载)
• awesome-tts-colab - GitHub Link
• awesome-starred - nari-labs/dia - A TTS model capable of generating ultra-realistic dialogue in one pass. (Python)
• awesome-opensource-ai - Dia (Nari Labs) - 1.6B parameter TTS generating ultra-realistic dialogue in one pass with nonverbal communications (laughter, coughing). Emotion and tone control via audio conditioning.  (2. Open Foundation Models)
• awesome-side-quests - nari-labs/dia - realistic multi-speaker dialogue in a single pass — demos are uncanny (Stale / LLM Apps & Interfaces)