Tag
Miso Labs releases Miso TTS 8B, a text-to-speech model based on the Sesame CSM architecture with a Llama 3.2-style backbone, designed for high-quality conversational speech generation and voice continuation.
This paper introduces Live Music Diffusion Models (LMDMs), which modify the diffusion process to enable efficient block-wise processing and novel training paradigms for real-time interactive music generation on consumer hardware, outperforming discrete autoregressive models in inference complexity and enabling stable post-training alignment.
WavFlow is a new method from Meta AI that generates synchronized, high-fidelity audio from video and text inputs directly in raw waveform space, bypassing latent compression. It achieves performance on par with latent-based methods on VGGSound and AudioCaps benchmarks.
Stability AI released Stable Audio 3.0, an open-weight model family for variable-length audio generation up to six minutes, with support for LoRA fine-tuning and audio inpainting, trained on fully licensed data.
Stable Audio 3 introduces a family of fast latent diffusion models for variable-length audio generation and editing, with open-source release of small and medium model weights.
Stability AI releases Stability Audio 3.0, a family of audio models capable of generating professional-grade music up to 6 minutes long, with open-weight versions for smaller models and licensed training data.
WavFlow generates high-fidelity audio directly in raw waveform space using waveform patchify and amplitude lifting, achieving competitive performance on video-to-audio and text-to-audio benchmarks without intermediate latent representations.
Stability AI releases Stable Audio 3, a family of latent diffusion models for variable-length audio generation and editing, with weights for small and medium models available on Hugging Face.
Dramabox, a new open-source voice AI model from Resemble AI, claims to provide both high-quality performance and verifiable signatures for authenticity.
A community member shares their hands-on experience generating a track using Google's Lyria 3 Pro via its API, noting the minimal cost and initial quality of the output.
Shanghai Jiao Tong University has open-sourced the F5-TTS speech generation model, trained on 100,000 hours of data, supporting bilingual synthesis in Chinese and English and zero-shot voice cloning, and allowing commercial use.
Google released Gemini 3.1 Flash TTS, a new text-to-speech model accessible via the Gemini API that supports advanced prompt-based control for detailed voice direction, accents, and speaking styles. The model enables sophisticated audio generation including multi-speaker conversations and character-specific vocal performances.
Google DeepMind releases Gemini 3.1 Flash TTS, an advanced text-to-speech model featuring new Audio Tags that enable fine-grained control over vocal style, delivery, and pace through text commands.
VoxCPM2 is an open-source, tokenizer-free diffusion autoregressive Text-to-Speech model supporting 30 languages with 2B parameters, 48kHz audio output, and features including voice design from natural language descriptions, controllable voice cloning, and real-time streaming capabilities.
Fish Audio S2 is an open-source text-to-speech system featuring multi-speaker capabilities, multi-turn generation, and instruction-following control, backed by a production-ready inference engine with low latency.
Lightricks released LTX-2.3, an open-weight diffusion-based audio-video foundation model with improved quality and prompt adherence, available in multiple checkpoints including distilled and LoRA variants for local execution.
OpenAI has released Sora 2, a state-of-the-art video and audio generation model featuring improved physics simulation, synchronized audio, enhanced steerability, and broader stylistic range. The system card outlines capabilities, safety measures, and a phased rollout via sora.com, a new iOS app, and future API access.
This paper introduces Continuous Audio Language Models (CALM), which generate audio using continuous frames instead of discrete tokens to improve fidelity and reduce computational cost in speech and music generation.
Google announces Gemini 2.5's advanced native audio capabilities, enabling real-time conversational AI with natural speech generation, style control, and multimodal understanding across 24+ languages.
A tool that generates audio using SUN and allows you to send it directly to your Spotify library.