Gemini 3.8 text-to-speech(blog.google)
310 points by swolpers | 137 comments
Google blog post announcing Gemini 3.8 Flash TTS and Flash-Lite TTS audio generation models, available across AI Studio, Gemini API, and other Google products.
#speech-synthesis on Hacker News
12 stories tagged speech-synthesis, newest first.
Qwen3-TTS family is now open sourced: Voice design, clone, and generation(qwen.ai)
697 points by Palmik | 212 comments
Qwen team blog post announcing the open-source release of the Qwen3-TTS model family for voice design, voice cloning, and speech generation.
Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU(github.com)
331 points by sammyyyyyyy | 116 comments
GitHub repository for Sopro, a lightweight 169M-parameter text-to-speech model with zero-shot voice cloning that runs on CPU, under Apache-2.0.
VibeVoice: A Frontier Open-Source Text-to-Speech Model(microsoft.github.io)
406 points by lastdong | 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.
Chatterbox TTS(github.com)
630 points by pinter69 | 182 comments
GitHub repository for Chatterbox, Resemble AI's open-source state-of-the-art text-to-speech model released under the MIT license.
Show HN: Dia, an open-weights TTS model for generating realistic dialogue(github.com)
584 points by toebee | 170 comments
GitHub repository for Dia, an Apache-2.0 licensed open-weights text-to-speech model by Nari Labs that generates realistic dialogue in one pass.
Crossing the uncanny valley of conversational voice(sesame.com)
346 points by monroewalker | 179 comments
Sesame research post by Brendan Iribe, Ankit Kumar and team on building natural-sounding conversational voice AI, with an interactive demo.
OpenVoice: Versatile instant voice cloning(research.myshell.ai)
387 points by ulrischa | 220 comments
MyShell research page introducing OpenVoice, an instant voice cloning method with style control and zero-shot cross-lingual cloning, linking to paper and code.
WhisperSpeech – An open source text-to-speech system built by inverting Whisper(github.com)
405 points by nickmcc | 102 comments
GitHub repository for WhisperSpeech, Collabora's open source text-to-speech system built by inverting OpenAI's Whisper model.
OpenVoice: Versatile Instant Voice Cloning(arxiv.org)
365 points by saeedesmaili | 171 comments
arXiv paper introducing OpenVoice, a voice cloning method that replicates a speaker's voice from a short clip with style control and zero-shot cross-lingual support.
StyleTTS2 – open-source Eleven-Labs-quality Text To Speech(github.com)
668 points by sandslides | 220 comments
GitHub repository for StyleTTS 2, an open-source text-to-speech model using style diffusion and adversarial training with large speech language models.
Launch HN: Vocode (YC W23) – Library for voice conversation with LLMs
322 points by KianHooshmand | 111 comments
Launch HN post for Vocode, a YC W23 open source Python library for building real-time voice conversation apps on top of LLMs.