Miso Labs
Emotive foundation voice models
About Miso Labs
Miso Labs is building the world’s most emotive foundation models for voice. We believe that the next generation of AI interactions shouldn't just be functional—they should be human. By bringing warmth and lightning-fast speed to the voice layer, we empower developers to build voice agents that users truly love.
Public traction evidence
Each signal links to the public source used for attribution.
- GitHub
MisoLabsAI/MisoTTS
MisoLabsAI/MisoTTS. YC S2026 snapshot lists Miso Labs with X handle MisoLabsAI; repo owner MisoLabsAI and repo title identify Miso TTS.
- YouTube
Launching Miso One: The Most Emotive AI Voice Model
Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso 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...
- YouTube
Miso One Demo: TikTok Voiceover
This entire voiceover was generated by Miso One, the most emotive voice model in the world. Miso 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...
- YouTube
Miso One Demo: Sports Voiceover
This entire voiceover was generated by Miso One, the most emotive voice model in the world. Miso 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...
- X
“AI contributed basically zero to GDP” says less about AI than about GDP.
“AI contributed basically zero to GDP” says less about AI than about GDP. Even before the AI boom, GDP failed to count data, the main input to AI. This paper estimates measured GDP would be 4% to 6% higher if data were counted. Imagine how this graph would look in 2026. From
- YouTube
We Cloned Sal Khan
This entire voiceover was generated by Miso One, the most emotive voice model in the world. Miso 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...
- X
getting your kid a summer job is a luxury imo
getting your kid a summer job is a luxury imo