Search Results for "context"

...A key innovation is its use of continuous acoustic and semantic speech tokenizers operating at an ultra-low frame rate of 7.5 Hz, enabling high audio fidelity with efficient processing of long sequences. The model integrates a Qwen2.5-based large language model with a diffusion head to produce realistic acoustic details and capture conversational context. Training involved curriculum learning with increasing sequence lengths up to 65K tokens, allowing VibeVoice to handle very long dialogues effectively. Safety mechanisms include an audible disclaimer and imperceptible watermarking in all generated audio to mitigate misuse risks.

FireRedTTS2 is a next-generation open-source text-to-speech (TTS) system focused on long-form, streaming speech synthesis for multi-speaker dialogue, delivering stable natural speech with context-aware prosody and reliable speaker transitions that support real-time and conversational applications. It features a specialized streaming speech tokenizer and a dual-transformer architecture that enables low latency and high-quality synthesis, making it suitable for interactive systems like chatbots, podcasts, and applications where dynamic turn-taking between speakers is essential. ...

VoxCPM2 is an advanced open-source text-to-speech system that redefines speech synthesis by eliminating traditional tokenization and instead generating continuous speech representations through a diffusion-based autoregressive architecture. Built on top of the MiniCPM model family, it enables highly natural, expressive, and context-aware speech generation that adapts tone, emotion, and pacing directly from input text. The system is trained on massive multilingual datasets, enabling support for dozens of languages and dialects while maintaining high fidelity and realism in generated audio. VoxCPM stands out for its ability to perform voice cloning with minimal input, capturing not only the speaker’s timbre but also nuanced features such as rhythm, accent, and emotional delivery. ...

...GLM-4-Voice builds upon the bilingual strengths of the GLM architecture, supporting both Chinese and English, and is designed to handle long-form conversations with context retention. The repository provides model weights, inference demos, and setup instructions for deploying speech-enabled AI systems.

Miso TTS is an advanced 8-billion-parameter text-to-speech model developed by Miso Labs for generating highly expressive and natural-sounding conversational speech. Built on an RVQ Transformer architecture inspired by Sesame CSM, it combines a powerful Llama-based backbone with an autoregressive audio decoder to produce high-quality audio from text. The model supports both standard speech synthesis and voice-conditioned generation using optional audio prompts for voice cloning. Miso TTS...

...During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that VALL-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find VALL-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis.