VoxCPM is an innovative tokenizer-free end-to-end text-to-speech (TTS) system that overcomes the limitations of discrete tokenization by modeling speech in a continuous space. It has two core capabilities: context-aware speech generation and realistic zero-shot voice cloning. It can automatically adjust the prosody and style according to the text content and clone the speaker's timbre, accent, and emotion with just a short reference audio.

Audio ProcessingSafetensorsMultiple Languages

This is a statically quantized GGUF version of the Manoghn/voicecraft-mistral-7b model, based on the Mistral-7B architecture, specifically designed for content generation and text generation tasks. This version offers multiple quantization levels, ranging from 2.8GB to 14.6GB. Users can choose the appropriate version according to their hardware conditions and performance requirements.

Natural Language ProcessingTransformersEnglish

MOSS-TTSD is an open-source bilingual spoken dialogue synthesis model that supports Chinese and English. It can convert two-person dialogue scripts into natural and expressive dialogue voices. It supports voice cloning, and the maximum duration of single-round voice generation can reach 1700 seconds.

Audio ProcessingSafetensorsMultiple Languages

A multilingual voice conversion and text-to-speech model that continues pre-training based on Qwen/Qwen3-1.7B-Base, supporting multilingual and multi-speaker voice generation and conversion functions.

MultimodalTransformers

NeuTTS Air is the world's first ultra-realistic on-device text-to-speech model with instant voice cloning capabilities. It is built on a large language model backbone with 0.5B parameters and can achieve natural speech generation, real-time performance, and speaker cloning on local devices.

Audio ProcessingGguf

vibevoice-gguf is a text-to-speech system based on the Microsoft VibeVoice-1.5B model. It runs through the gguf-connector and can convert text into natural speech. It supports voice cloning and multi-speaker voice generation.

Audio ProcessingGguf

Step-Audio 2 is an end-to-end multimodal large language model designed to meet the industry-level audio understanding and voice dialogue needs. It has advanced voice and audio understanding capabilities, intelligent voice dialogue functions, tool invocation, and multimodal retrieval enhanced generation capabilities, and has achieved leading performance in multiple audio understanding and dialogue benchmark tests.

MultimodalTransformers

MGM-Omni-TTS-2B is the voice generation component of the MGM-Omni full-featured chatbot, specifically designed for text-to-speech conversion. It supports zero-shot voice cloning in Chinese and English, can generate smooth and natural voices longer than 10 minutes, and achieve efficient streaming audio generation.

MultimodalTransformersMultiple Languages

viⓍTTS is a voice generation model capable of cloning voices into different languages using a 6-second short audio clip.

A cutting-edge voice large model based on the Llama architecture, designed for high-quality, empathetic text-to-speech generation

Audio ProcessingTransformersEnglish

CSM is a 1-billion-parameter voice generation model developed by Sesame, capable of generating RVQ audio encoding from text and audio inputs

Audio ProcessingSafetensorsEnglish

A Ukrainian-specific speech synthesis model fine-tuned based on Fish Speech 1.5, supporting high-quality voice generation for 55 speakers

ⓍTTS-v2 is an advanced voice generation model that supports 17 languages. It can clone voices and achieve cross-lingual voice synthesis with just a 6-second audio clip.

An English speech synthesis (TTS) model fine-tuned based on Microsoft's SpeechT5, specializing in voice generation for technical domain texts

Audio ProcessingTransformersEnglish

This is a fine-tuned version of the XTTS v2 model developed by Coqui-AI, specifically optimized for Hindi speech datasets, supporting voice cloning and multilingual speech generation.

ⓍTTS is a voice generation model that can clone a voice with just 6 seconds of audio and apply it to different languages, supporting Argentinian-accented Spanish.

ⓍTTS is a speech generation model that can clone voices with just 6 seconds of audio and apply them to different languages. No need for hours of extensive training data.

viⓍTTS is a voice generation model that supports voice cloning in 18 languages, with special optimization for Vietnamese.

Audio ProcessingTransformersOther

viⓍTTS is a voice generation model supporting 18 languages, specifically optimized for Vietnamese, achieving cross-lingual voice cloning with just 6 seconds of audio.

Audio ProcessingTransformersOther

Kotoba-Speech v0.1 is a Japanese speech generation model based on a 1.2B parameter Transformer, supporting text-to-speech and one-shot voice cloning.

Audio ProcessingTransformersJapanese