InterconnectsInterconnects Artifacts Hub
withVAILVAIL
All models

MoshiVis

byKyutaiKyutai· 27 Jan 2025
MultimodalAudio generation

An image-capable extension of the text-to-speech moshi model, which uses PaliGemma 2 as its encoder.

Specs
Params7B
LicenseCC-BY-4.0
Tags
models/llmsmodels/llms/multi-modalmodels/audio-generation
Resources
Hugging Face — kyutai/moshika-vis-pytorch-bf16Paper / tech reportAppeared in Artifacts Log #9
How these metrics work
Adoption · Hugging Face
RAM score
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Hugging Face Downloads
0
last 30d
0
all time
HF Likes
59

Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.

Related Models

More from Kyutai

Kyutai STT 2.6B English
KyutaiKyutai06 Jun 2025
Helium-1-2b
KyutaiKyutai30 Apr 2025
Hibiki-M MLX
KyutaiKyutai04 Feb 2025
moshiko-pytorch-bf16
KyutaiKyutai11 Sep 2024

Similar Models

Qwen2.5-Omni-7B
QwenQwen22 Mar 2025
multimodalaudio generation7B params
MiMo-Audio-7B-Instruct
Xiaomi MiMoXiaomi MiMo18 Sep 2025
multimodalaudio generation7B params
Ming-Lite-Omni
Inclusion AIInclusion AI28 May 2025
multimodalaudio generation19B params
Ming-Lite-Omni-1.5
Inclusion AIInclusion AI15 Jul 2025
multimodalaudio generation20.3B params