Moshi AI vs Google Flow Music (formerly Riffusion)

Moshi AI is a speech-native conversational model from Kyutai, a Paris-based open-science research lab. Instead of chaining speech recognition, text generation, and text-to-speech, Moshi processes audio directly and holds full-duplex voice conversations with minimal latency.

Its multi-stream design runs separate channels for the user, Moshi's spoken output, and an Inner Monologue text stream that improves coherence. That setup lets Moshi listen and talk at the same time, handle overlaps, interruptions, and backchanneling like a real conversation rather than rigid speaker turns.

Moshi is built on Helium, a 7B language model, and Mimi, Kyutai's neural audio codec. Weights and inference code ship for PyTorch, Rust, and MLX, and you can try it in the browser at moshi-chat.kyutai.org. Researchers, voice AI developers, and anyone building real-time spoken interfaces will find the most value here.

Google Flow Music lets you create full-length songs, remix tracks, and publish music through a conversational studio built on Google's Lyria 3.5 model. riffusion.com now redirects to flowmusic.app, where you chat with Producer like you are in a session, iterate on vocals and arrangement, and export finished tracks.

Unlike one-shot music generators that spit out a clip and stop, Flow Music focuses on iterative editing. Replace and Extend let you swap specific sections or continue a song past its endpoint without regenerating the whole track. You can also direct Veo-powered music videos, split stems, apply audio effects, and vibe-code custom instruments or mini apps inside Spaces.

The free tier includes daily top-up credits and two concurrent generations with no credit card required. Paid plans raise monthly credits, concurrent generation limits, and add member perks. Google acquired the Riffusion team in 2026 and folded the product into Google Labs alongside Lyria and Veo.