4 مستودعات
Audio generation that uses a specific reference sample to condition the output identity.
Distinct from Audio Synthesis: Focuses on conditioning synthesis using a reference sample, whereas general audio synthesis covers all artificial signal generation.
Explore 4 awesome GitHub repositories matching graphics & multimedia · Reference-Driven Synthesis. Refine with filters or upvote what's useful.
MockingBird is an AI voice cloning tool and text-to-speech system designed to generate synthetic speech. It functions as a voice synthesis trainer for building custom models from audio datasets, a command-line generator for producing audio files, and a text-to-speech server for remote application integration. The project specializes in real-time voice cloning, which extracts vocal characteristics from short audio samples to mimic a target speaker's unique timbre. It utilizes reference-driven audio synthesis to condition pre-trained models on specific audio samples, allowing for the generation
Generates arbitrary speech conditioned on a specific audio sample to maintain voice identity.
AudioGPT is an LLM-driven audio framework and processing suite that uses large language models to orchestrate neural audio pipelines. It functions as a multimodal audio generator and processing system, integrating a collection of pretrained models to handle speech synthesis, sound generation, and audio manipulation. The system is distinguished by its ability to generate audio from diverse inputs, including text and images, and its capacity to produce synchronized talking head videos. It also operates as a neural speech translator, converting spoken language between different tongues while pre
Translates natural language descriptions into structured control signals to parameterize audio generation models.
ChatTTS-ui هو واجهة ويب وغلاف لواجهة برمجة التطبيقات (API) لنموذج ChatTTS، مصمم لتحويل النصوص المكتوبة والمدخلات متعددة اللغات إلى صوت مسموع. يعمل كلوحة تحكم لتوليد الكلام بالذكاء الاصطناعي ومولد برمجي لإنشاء مخرجات صوتية طبيعية. يركز المشروع على تخصيص ملفات تعريف الصوت والتحكم في فروق الكلام الدقيقة. يسمح بالحفاظ على خصائص متحدث متسقة باستخدام قيم البذور (Seeds) وملفات البيانات، مع توفير عناصر تحكم في النبرة والضحك والتوقفات من خلال مطالبات سلوكية ومعلمات أخذ العينات. يتضمن النظام معمارية عميل-خادم تتعامل مع معالجة الصوت غير المتزامنة وتوفر واجهة برمجية لتكامل التطبيقات الخارجية. يدير ملفات تعريف الصوت وتكوينات الصوت عبر واجهة مدارة الحالة لضمان توليد متسق.
Allows fine-tuning of voice nuance and tone using behavioral prompts and sampling parameters.
ACE-Step is a high-fidelity audio synthesis system and diffusion model designed to generate music and vocals from text descriptions. It functions as a music generator and vocal synthesizer, using a diffusion transformer decoder to produce audio across various languages and genres. The project provides tools for text-guided audio editing, including the ability to extend the duration of tracks, regenerate specific song segments, and perform latent-space audio inpainting to modify lyrics or styles. It also includes a framework for audio style fine-tuning using low-rank adaptation to adapt vocal
Synthesizes complementary instrument stems by conditioning the model on reference audio latent features.