moshi
moshi is Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.. It is ranked #112 on the Stars Radar, in Models & inference, first seen 100 days ago and shared in 1 post (11.1k views).
Alternatives to moshi
- colibri — Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine,…
- models.dev — An open-source database of AI models.
- VoxCPM — VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
- parakeet — OpenAI Whisper-compatible ASR server using NVIDIA Parakeet TDT 0.6B (ONNX). Super fast CPU/GPU transcriptions
- OmniVoice — High-Quality Voice Cloning TTS for 600+ Languages
- whisper.cpp — Port of OpenAI's Whisper model in C/C++
moshi in numbers
- Rank on the Stars Radar: #112 of 209
- Shared in 1 post by 1 account: @kyutai-labs
- 11.1k views on those posts
- First seen 100 days ago, last shared 10 days ago
- Pricing seen by Jev: open source
- Market: Models & inference
FAQ
What is moshi?
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec. It was first shared on X 100 days ago and is ranked #112 on the Stars Radar.
Is moshi free?
It is open source.
Who shared moshi?
1 account on X, including @kyutai-labs, in 1 post totalling 11.1k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 209 posts from 1 X accounts over the last 365 days, 209 tools, 10 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 16:59 UTC. Full method.