multimodal LLM
Moshi (Moshiko)
Full-duplex speech-text foundation model for real-time spoken dialogue, listening and speaking at the same time; Moshiko is the male-voice version.
Levelmodel
Classmultimodal LLM
Parameters7.69B
Contextnot in the notes
Released11 Sep 2024
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer
- Total parameters
- 7.69B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- Parameter count from the safetensors index on Hugging Face.
- Context length
- not in the notes
- Input
- text, audio
- Output
- text, audio
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- Creative Commons Attribution 4.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- Model card languages: en
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperKyutaifrontier lab
Kyutaifrontier labModelMoshi (Moshiko)Kyutai, multimodal LLM
Moshi (Moshiko)Kyutai, multimodal LLMR&D TopicsReal-Time Spoken Dialogue and Low-Latency Voice GenerationAudio Language Models for Speech Understanding
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 1
R&D topics 2
Audio Language Models for Speech UnderstandingLanguage models that take audio as input to transcribe, answer questions about and conver…exemplarReal-Time Spoken Dialogue and Low-Latency Voice GenerationModels that listen and speak with delays of a few hundred milliseconds, including full-du…exemplar
Sources
- github.com/kyutai-labs/moshi https://github.com/kyutai-labs/moshi
- huggingface.co/kyutai/moshiko-pytorch-bf16 https://huggingface.co/kyutai/moshiko-pytorch-bf16
- huggingface.co/api/models?pipeline_tag=audio-to-audio&sort=d... https://huggingface.co/api/models?pipeline_tag=audio-to-audio&sort=downloads&limit=50
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Moshi (Moshiko)", https://aurion.semai.id/models/kyutai-moshiko/, records of October 2026.