Skip to content
Local AI Wizard
Your machine
Theme

Local audio models

Speech to speech / audio to audio · Speak, transcribe, convert audio, music and sound effects.

No ranking for this task yet

No public, reusable score covers two or more of these models. Artificial Analysis arena results stay withheld: their free tier allows internal use only.

Audio models

3 models · 17 reviewed · checking Sep 26, 2026 

Audio models
LFM2.5-Audio-1.5BLiquid AI · Publisher terms1.5Publisher terms
moshiko-pytorch-bf16Kyutai · CC BY 4.07.7CC BY 4.0
personaplex-7b-v1NVIDIA · Publisher terms8.4Publisher terms

No Documented memory · GB column: no publisher documents a memory path for these models. No Languages column: neither the Hub cards nor the publishers' pages name their languages. No Released column: no publisher release date is recorded for these models (Hub repository dates are not release dates).

Catalog

3 models · 0 with documented memory

Choose your machine and the charts and tables mark what fits in its memory.