Fish-Speech 1.5
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
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
- 24 November 2024
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.
- Training data
- 700,000,000,000 tokens
[tokens] Their previous model was trained on 720000 hours of audio data that was equal to 5*10^11 tokens -> 1M hours ~ 7*10^11 tokens model trained on more than 1 million hours of audio data in multiple languages.
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
- 2.7 × 10²¹ FLOP
- How it was established
- Comparison with other models
Previous model Fish-Speech 1.4 used 1.9151355e+21 FLOP for training (see model card) and was trained on 720000 hours of audio, while this model is similar but trained on 1M hours of audio -> its training compute couldbe estimated as 1.9151355e+21 * 10^6 / 720000 = 2.6599104e+21 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
- Open — downloadable
- Model access
- Open weights (non-commercial)
- Training code
- Open source
- Hugging Face
- fishaudio
weights are released under CC-BY-NC-SA-4.0 License https://huggingface.co/fishaudio/fish-speech-1.5 This codebase is released under Apache License 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
- Fish Speech V1.5 is a leading text-to-speech (TTS) model trained on more than 1 million hours of audio data in multiple languages.
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Fish-Speech 1.5 was published by Fish Audio, in United States of America, in November 2024. industry is the category the publisher falls under.
It works in Speech, and is recorded as doing speech synthesis, Text-to-speech (TTS).
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the fishaudio organisation on Hugging Face.
How it was trained
Producing it required around 2.7 × 10²¹ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
Around 700,000,000,000 tokens went into training it.
Answers
Fish-Speech 1.5 — common questions
How much compute was used to train Fish-Speech 1.5?
Around 2.7 × 10²¹ 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.
What GPU do I need to run Fish-Speech 1.5?
We cannot say. Fish-Speech 1.5 has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
Is Fish-Speech 1.5 open source?
Its weights are published, so Fish-Speech 1.5 can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
How many parameters does Fish-Speech 1.5 have?
No parameter count has been published for Fish-Speech 1.5, which is why no memory or speed figure appears on this page.
Who created Fish-Speech 1.5?
Fish-Speech 1.5 was published by Fish Audio, based in United States of America, categorised as industry.
When was Fish-Speech 1.5 released?
Fish-Speech 1.5 was published in November 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Fish-Speech 1.5 used for?
Fish-Speech 1.5 works in Speech, and is recorded as handling speech synthesis, Text-to-speech (TTS). These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download Fish-Speech 1.5?
Its weights are published under the fishaudio organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.
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.