{"id":102518,"title":"Miso Labs - emotive voice models","tagline":"Building the most emotive voice AI models","body":"Today, we’re excited to introduce **Miso One, the most emotive voice model in the world.**\n\nMiso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency.\n\nWe’ve open-sourced the model weights, with API access coming soon.\\\n\\\n[**https://www.youtube.com/watch?v=HizlJgDbac8**](https://www.youtube.com/watch?v=HizlJgDbac8)\n\nAll of these voiceovers were generated by Miso One!\n\n[**https://www.youtube.com/watch?v=QX6a_lUdwC8**](https://www.youtube.com/watch?v=QX6a_lUdwC8)\n\n[**https://www.youtube.com/watch?v=ywH2C4LKu9E**](https://www.youtube.com/watch?v=ywH2C4LKu9E)\n\n[**https://www.youtube.com/shorts/jTLNoUH85iY**](https://www.youtube.com/shorts/jTLNoUH85iY)\\\n\\\n**_Our ask:_**\\\nCheck out our repository and give us a star!\n\n[**https://github.com/MisoLabsAI/MisoTTS**](https://github.com/MisoLabsAI/MisoTTS)\n\nYou can also test out the model directly at [**misolabs.ai**](http://misolabs.ai).","slug":"QfW-miso-labs-emotive-voice-models","created_at":"2026-06-03T17:54:30.376Z","updated_at":"2026-06-20T18:26:15.990Z","total_vote_count":16,"url":"https://www.ycombinator.com/launches/QfW-miso-labs-emotive-voice-models","share_image_url":"//bookface-static.ycombinator.com/assets/ycdc/yc-og-image-c440a0ad1dacfb86eeeb343717479cc54d256614449b4ef719977a0a451f8bc8.png","company":{"id":30723,"name":"Miso Labs","slug":"miso-labs","url":"https://misolabs.ai","logo":"https://bookface-images.s3.amazonaws.com/small_logos/8dd28df9a99151aedfe26a296d8e112af2bf4edb.png","batch":"Spring 2026","industry":"B2B","tags":[],"search_path":"https://bookface.ycombinator.com/company/30723"}}