OpenAudio-S1
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Fish Audio
- Organisation type
- Industry
- Country
- United States of America
- Published
- 3 June 2025
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Speech
- Task
- Speech synthesis, Text-to-speech (TTS)
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 4B
- Training data
- 1,400,000,000,000 tokens
"the 4-billion parameter S1 model"
[tokens] Their previous model was trained on 720000 hours of audio data that was equal to 5*10^11 tokens -> 2M hours ~ 14*10^11 tokens "Trained on 2 million hours of audio, OpenAudio S1 achieves breakthrough quality and diversity in voice generation. This vast dataset enables the model to produce smooth, realistic voices nearly indistinguishable from human voiceovers."
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 3.4 × 10²² FLOP
- How it was established
- Operation counting
6 FLOP / parameter / token * 4 * 10^9 parameters * 14 * 10^11 token [see training dataset size note] = 3.36e+22 FLOP
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- API access
- Training code
- Unreleased
Here is a codebase for their previous model (Fish-Speech, Apache License) but not his one https://github.com/fishaudio/fish-speech/tree/main/fish_speech
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Our cutting-edge text-to-speech model that performs like voice actors
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
OpenAudio-S1 was published by Fish Audio, in the country recorded as United States of America, during June 2025. The category the publisher falls under is industry.
It works in the domain of Speech, and is recorded as performing the task of speech synthesis, Text-to-speech (TTS).
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
What went into building it
The training run consumed about 3.4 × 10²² FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 1,400,000,000,000 tokens of text.
Answers
OpenAudio-S1 — common questions
OpenAudio-S1— what is it used for?
It works in the domain of Speech, and is recorded as handling the task of speech synthesis, Text-to-speech (TTS). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
OpenAudio-S1— how much compute was used to train it?
Training consumed around 3.4 × 10²² FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
OpenAudio-S1— what GPU do I need to run it?
None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
OpenAudio-S1— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
OpenAudio-S1— how many parameters does it have?
It has a parameter count of 4B. "the 4-billion parameter S1 model". That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
OpenAudio-S1— who created it?
It was published by Fish Audio, based in United States of America, an organisation categorised as industry.
OpenAudio-S1— when was it released?
It was published in June 2025.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.