Top AI Product

## What it is

MisoTTS is an 8-billion-parameter text-to-speech model from Miso Labs, released with open weights and a claim of being the most emotive voice model around. It generates expressive speech from text plus audio context, using residual vector quantization to widen its sonic range, and it clones a voice from a short sample in one shot. Latency is the headline: roughly 110 milliseconds, faster than a human reaction.

## Why it matters

The architecture is a Llama 3.2-style backbone paired with a smaller audio decoder, inspired by Sesame’s CSM design. The bigger deal is the license: Miso shipped the weights open on day one, so you can self-host and keep audio off third-party servers — a real concern for anyone building voice agents on sensitive calls. API access is coming, but open-weights-first is the opposite of how most frontier voice labs operate. For developers who want human-sounding, low-latency speech without handing data to a vendor, MisoTTS is an unusually open option.