Model · Voice and speech

OpenAudio S1

A text-to-speech model from the team behind Fish Audio that reads text in 13 languages and lets you add emotion tags like (sad) or (whispering). The full model runs on Fish Audio; a smaller version can be downloaded for non-commercial use only.

Go to OpenAudio S1’s website

At a glance

Open or closed: Downloadable, with conditions
You can download and run it, but the licence limits use
Only S1-mini (0.5B) is downloadable, behind a gate where you agree to non-commercial use. The full 4B S1 was only seen on Fish Audio's own platform.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Licence: CC BY-NC-SA 4.0 (S1-mini weights) (Non-commercial only)
Licence tag from the Hugging Face model metadata; the card page itself could not be fetched. Gate checkbox: 'use this model for non-commercial use ONLY'.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: No
Applies to the downloadable S1-mini. Commercial terms for using full S1 through Fish Audio's paid service were not checked.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Cost: Free option: S1-mini free to download for non-commercial use; you pay for your own hardware
Plans below.
How you use it: On your own computer, Through another service, In your browser
Full S1 (4B) via the Fish Audio playground at fish.audio; S1-mini weights on Hugging Face (gated), run with the fish-speech code.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: Technical
Running locally needs the fish-speech code; the Fish Audio playground needs no setup.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: Hanabi AI Inc. (OpenAudio / Fish Audio)
OpenAudio is the research lab of Hanabi AI Inc.; Fish Audio is its product platform. No country stated on the page read.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

What you can make with it

A voice or speech, read my text aloud (main use)

text to audio

Emotion, tone and sound markers (e.g. laughing, sighing). The S1 page doesn't mention voice cloning, so it is not listed.

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

S1 page quotes '$15 per million bytes (about $0.8 per hour)' without saying which product it applies to; Fish Audio pricing not checked, so no plan listed.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Where you can run it

Hugging Face

Other options for “A voice or speech, read my text aloud”

Adobe Firefly, Akool, Amazon Polly, Arcads, Async (formerly Podcastle), Azure AI Speech, Bark, CAMB.AI, Cartesia, Chatterbox, Clipchamp, Deepgram, DeeVid AI, Descript, Dia, Dubverse, Eleven v3, ElevenLabs, F5-TTS, fal, Filmora, Fish Audio, FlexClip, Fliki

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.