VibeVoice-Large-Q8 is the first truly usable 8-bit VibeVoice model. Through selective quantization technology, it significantly reduces the model size while maintaining the same audio quality as the original model, making it suitable for scenarios with limited video memory.

Audio ProcessingTransformersMultiple Languages

Gemma 3n is a lightweight, state-of-the-art multimodal open model launched by Google, built on Gemini technology. It is designed for low-resource devices, supporting text, image, video, and audio inputs and generating text outputs. It uses selective parameter activation technology to run efficiently with a 4B parameter scale.

MultimodalTransformersEnglish

DeSTA2.5-Audio is a general large audio language model that achieves high scalability and efficiency through self-generated cross-modal alignment technology without the need for specific task instruction tuning data. It also retains language capabilities and avoids catastrophic forgetting.

MultimodalTransformers

MiDashengLM is an efficient audio understanding model. With the help of universal audio captioning technology, it can excellently complete various audio understanding tasks and shows outstanding performance and efficiency. This model outperforms similar models in multiple key audio understanding tasks, with high - efficiency inference speed and comprehensive audio understanding ability.

MultimodalSafetensorsMultiple Languages

Gemma 3n is a lightweight and state-of-the-art open-source multimodal model family launched by Google, built on the same research and technology as the Gemini model. It supports text, audio, and visual inputs and is suitable for various tasks.

MultimodalTransformers

Gemma 3n is a lightweight and state-of-the-art open-source multimodal model family launched by Google. It is built on the same research and technology as the Gemini model and supports text, audio, and visual inputs.

MultimodalTransformers

This is a quantized version of the OpenAI whisper-large-v3 model, which significantly improves inference performance through INT8 weight quantization technology and is specifically designed for efficient audio-to-text conversion tasks.

Audio ProcessingTransformersEnglish

InspireMusic is a unified framework focused on music generation, song generation, and audio generation, integrating autoregressive transformers with flow-matching models through audio tokenization technology, supporting high-quality long audio generation.

Audio ProcessingSafetensorsEnglish

Tango 2 is an improved text-to-audio generation model based on Tango, achieving alignment training for audio generation through Direct Preference Optimization (DPO) technology

Audio ProcessingTransformersEnglish

This is a voice conversion model based on RVC (Retrieval-based Voice Conversion) technology, capable of transforming input audio into Pikachu-style speech.

Audio ProcessingTransformers

This is a voice conversion model based on RVC (Retrieval-based Voice Conversion) technology, capable of transforming input audio into a voice resembling Barack Obama's.

Audio ProcessingTransformers

This is a voice conversion model based on RVC (Retrieval-based Voice Conversion) technology, capable of transforming input audio into a specific style of speech.

Audio ProcessingTransformers

This is a voice conversion model based on RVC (Retrieval-Based-Voice-Conversion) technology, capable of converting input audio into output audio with a specific timbre.

Audio ProcessingTransformers

A voice conversion model based on RVC technology that supports converting input audio into output audio with a specific timbre

Audio ProcessingTransformers

This is an audio conversion model based on RVC (Retrieval-based Voice Conversion) technology, capable of transforming input audio into speech with a specific style.

Audio ProcessingTransformers

This is a voice conversion model based on RVC (Retrieval-based Voice Conversion) technology, capable of transforming input audio into Harry Styles' distinctive vocal style.

Audio ProcessingTransformers

This is a voice conversion model based on RVC (Retrieval-based Voice Conversion) technology, capable of transforming input audio into output audio that mimics Billie Eilish's voice.

Audio ProcessingTransformers

This is a voice conversion model based on RVC (Retrieval-Based Voice Conversion) technology, specifically designed to transform input audio into Travis Scott-style speech.

Audio ProcessingTransformers

This is a voice conversion model based on RVC (Retrieval-based Voice Conversion) technology, capable of transforming input audio into Taylor Swift-style speech.

Audio ProcessingTransformers

This is a voice conversion model based on RVC (Retrieval-based Voice Conversion) technology, capable of transforming input audio into a specific character's voice.

Audio ProcessingTransformers