Plainly Guide

Plainly Guide › Voice and speech › LFM3-Audio

ModelVoice and speechDownloadable, with conditionsFree option

LFM3-Audio

Liquid AI's small audio model that runs on a laptop or phone. It transcribes speech in 18 languages, reads text aloud, translates, and holds a spoken conversation in English. Free for commercial use by companies under US$10M annual revenue.

Go to LFM3-Audio’s website
Free to try?Yes
Can I sell what I make?Yes, with conditions
Open or closedDownloadable, with conditions
Skill neededTechnical

The facts, with sources

Open or closed
Downloadable, with conditions
You can download and run it, but the licence limits use
source · checked 7 Nov 2026 · checked on the maker's own page
Licence
LFM Open License v1.0 (Community licence with conditions (e.g. revenue cap))
source · checked 7 Nov 2026 · checked on the maker's own page
Can I sell what I make?
Yes, with conditions
  • Only below a revenue limit
  • You must credit the maker
Commercial use only below US$10M annual revenue; keep licence and attribution notices.
source · checked 7 Nov 2026 · checked on the maker's own page
Cost
Free option: Free to download; you pay for your own hardware
Plans below.
How you use it
On your own computer
Transformers, vLLM, SGLang, llama.cpp, MLX.
source · checked 7 Nov 2026 · checked on the maker's own page
Skill needed
Technical
source · checked 7 Nov 2026 · checked on the maker's own page
Made by
Liquid AI, Inc.
source · checked 7 Nov 2026 · checked on the maker's own page
Status
Available
Date the weights appeared on Hugging Face.
source · checked 7 Nov 2026 · checked, but the page was unclear or partial

What you can make with it

audio to texttext to audioaudio to audio

source · checked 7 Nov 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

source · checked 7 Nov 2026 · checked on the maker's own page

Related

Where you can run it

Hugging Face

Other options for “A voice or speech, text from a recording”

Adobe Podcast (Enhance Speech), Adobe Premiere, AssemblyAI, Async (formerly Podcastle), AudioShake, Auphonic, Azure AI Speech, CAMB.AI, Cartesia, Cleanvoice AI, Clipchamp, Deepgram, Descript, Distil-Whisper, Dubverse, ElevenLabs, Filmora, Gling, Granite Speech 5.0, Happy Scribe, Hugging Face, Kapwing, Krisp, MacWhisper

About this entry. Facts last checked 7 Nov 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.

Spot an error? Tell us, with a link to the source. How corrections work