Model Detail

moshika-rl-seamless is an audio model with 3.8B parameters released by kyutai. The model is registered under the audio-to-audio pipeline tag on Hugging Face, distributed under the permissive cc-by-nc-4.0 license.

moshika-rl-seamless ships with 3.8B parameters. Total weight footprint is approximately 7.7 GB, which is the relevant figure when planning local-inference VRAM. The cc-by-nc-4.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.

moshika-rl-seamless is best fit for speech recognition, transcription, or speech synthesis depending on the task head. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.