Unsupervised speech-to-speech translation from monolingual data(blog.research.google)

37 points by atg_abhishek 2 years ago | 23 comments

SoundStorm: Efficient Parallel Audio Generation(google-research.github.io)

272 points by sh_tomer 3 years ago | 119 comments

NaturalSpeech 2: Zero-shot speech and singing synthesizers(speechresearch.github.io)

206 points by tim_sw 3 years ago | 93 comments

AudioPaLM: A Large Language Model That Can Speak and Listen(google-research.github.io)

78 points by ml_basics 3 years ago | 17 comments

VibeVoice: A Frontier Open-Source Text-to-Speech Model(microsoft.github.io)

406 points by lastdong 1 year ago | 150 comments

Project page for Microsoft's VibeVoice, an open-source TTS model generating up to 90 minutes of multi-speaker conversational audio using LLM and diffusion.

Llasa: Llama-Based Speech Synthesis(llasatts.github.io)

156 points by CalmStorm 1 year ago | 18 comments

Transcribe.cpp(workshop.cjpais.com)

696 points by sebjones 3 months ago | 144 comments

Project page announcing transcribe.cpp, a ggml-based speech transcription library supporting recent models, from the author of the Handy speech-to-text app.

Training language models to be warm and empathetic makes them less reliable(arxiv.org)

334 points by Cynddl 1 year ago | 333 comments

arXiv paper finding that fine-tuning language models to be warm and empathetic raises error rates and makes them more sycophantic on safety-critical tasks.

Gemini-3.5-Transcribe(blog.google)

338 points by k9294 1 month ago | 119 comments

Google blog post announcing Gemini 3.5 Transcribe, a speech-to-text model for precise real-time transcription.

NeuralSVG: An Implicit Representation for Text-to-Vector Generation(sagipolaczek.github.io)

726 points by lnyan 1 year ago | 69 comments

Project page for NeuralSVG, a research method from Tel Aviv University and MIT CSAIL that generates layered SVG vector graphics from text prompts using an implicit neural representation.

Google to invest up to $2B in Anthropic(reuters.com)

356 points by fofoz 3 years ago | 338 comments

Reuters news article reporting that Google agreed to invest up to $2 billion in OpenAI rival Anthropic, published October 27, 2023.

Gemini 3.8 Live and 3.8 Live Extended Thinking(blog.google)

479 points by leumon 1 month ago | 316 comments

Google blog post announcing Gemini 3.8 Live and 3.8 Live Extended Thinking, live voice dialogue models with improved intelligence and parallel reasoning.