Draft:Fish Audio
 | Review waiting, please be patient.
This may take 8 weeks or more, since drafts are reviewed in no specific order. There are 2,842 pending submissions waiting for review.
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
Reviewer tools
|
Submission declined on 12 September 2025 by Pythoncoder (talk).
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
This draft has been resubmitted and is currently awaiting re-review. |  |
| Fish Audio | |
|---|---|
| Developer(s) | Hanabi AI |
| Initial release | 2024 |
| Stable release | S1 / S1-mini
|
| Type | Text-to-speech |
| License | Proprietary (platform), Open source (selected models) |
| Website | fish |
Fish Audio is a text-to-speech (TTS) platform developed by the American artificial intelligence research company Hanabi AI. The platform provides speech synthesis and speech recognition using machine learning. Several of its TTS models have been released as open source on GitHub and Hugging Face.[1][2]
History
[edit]Fish Audio was launched on April 29, 2024 with the release of Fish Speech v1.0.0, an open-source text-to-speech model.[3][4]
On September 12, Fish Audio released Fish Speech v1.4, trained on approximately 700,000 hours of multilingual audio data.[5] Versions v1.5 and v1.6 followed later in December 2024 and March 2025.[6]
In March 2025, Hanabi AI, the developer of Fish Audio, was accepted into the HF0 Residency startup accelerator as part of its W25 cohort.[7]
On 2 June 2025, the platform introduced Fish Audio S1 (also known as OpenAudio S1), a 4 billion parameter model available on its web service. A distilled 0.5 billion parameter version, S1-mini, was released as open source on Hugging Face.[8][9]
Products
[edit]- Fish Speech v1.0–v1.6 – successive text-to-speech models released between 2024 and 2025, with multilingual support.[10]
- Fish Audio S1 – large-scale text-to-speech model (4B parameters) released in June 2025.[11]
- Fish Audio S1-mini – distilled version of S1 (0.5B parameters), released in June 2025 as open source on Hugging Face.[12]
Reception
[edit]36Kr reported in 2025 that Fish Audio had achieved around US$5 million in annual recurring revenue, citing Hanabi AI as an example of a lean AI company reaching notable scale.[13] MarkTechPost described Fish Speech v1.4 as a multilingual open-source TTS model with instant voice cloning and low-latency output.[14] Fish Audio has also been included in the Text-to-Speech Arena leaderboard maintained by ArtificialAnalysis.ai, which compares different speech synthesis systems.[15]
References
[edit]- ^ "Releases · fishaudio/Fish-speech". GitHub.
- ^ "Fishaudio (Fish Audio)". 25 March 2025.
- ^ "Release v1.0.0 · fishaudio/Fish-speech". GitHub.
- ^ https://fish.audio/
- ^ "Fish Audio Introduces Fish Speech 1.4: A Powerful, Open-Source Text-to-Speech Model with Multilingual Support, Instant Voice Cloning, and Lightning-Fast Performance". 13 September 2024.
- ^ "Releases · fishaudio/Fish-speech". GitHub.
- ^ https://www.bloomberg.com/news/features/2025-04-15/hf0-startup-accelerator-uses-meditation-to-push-founders?embedded-checkout=true
- ^ "Fishaudio/Openaudio-s1-mini · Hugging Face".
- ^ "Fish Audio Releases OpenAudio S1: A New Benchmark for AI Voice with Professional Dubbing Actor Quality".
- ^ "Releases · fishaudio/Fish-speech". GitHub.
- ^ "Fishaudio/Fish-speech". GitHub.
- ^ "Fishaudio/Openaudio-s1-mini · Hugging Face".
- ^ "新增10家上榜Ai应用小团队，他们靠"交付结果"年入千万美元-36氪".
- ^ "Fish Audio Introduces Fish Speech 1.4: A Powerful, Open-Source Text-to-Speech Model with Multilingual Support, Instant Voice Cloning, and Lightning-Fast Performance". 13 September 2024.
- ^ "Text to Speech Model Arena | Artificial Analysis".
- Promotional tone, editorializing and other words to watch
- Vague, generic, and speculative statements extrapolated from similar subjects
- Essay-like writing
- Hallucinations (plausible-sounding, but false information) and non-existent references
- Close paraphrasing
Please address these issues. The best way is usually to read reliable sources and summarize them, instead of using a large language model. See our help page on large language models.