15.ai

15.ai
Type of site
Artificial intelligence, speech synthesis, machine learning, deep learning
Available inEnglish
Founder(s)15
URL15.ai
CommercialNo
RegistrationNone
LaunchedInitial release: March 12, 2020; 4 years ago (2020-03-12)
Stable release: v24.2.1
Current statusUnder maintenance
Part of a series on
Artificial intelligence
Major goals
Approaches
Applications
Philosophy
History
Glossary

15.ai is a non-commercial freeware artificial intelligence web application that generates natural emotive high-fidelity[a] text-to-speech voices from an assortment of fictional characters from a variety of media sources.[4][5][6][7] Developed by a pseudonymous MIT researcher under the name 15, the project uses a combination of audio synthesis algorithms, speech synthesis deep neural networks, and sentiment analysis models to generate and serve emotive character voices faster than real-time, particularly those with a very small amount of trainable data.

Launched in early 2020, 15.ai began as a proof of concept of the democratization of voice acting and dubbing using technology.[8] Its gratis and non-commercial nature (with the only stipulation being that the project be properly credited when used), ease of use, no user account registration requirement, and substantial improvements to current text-to-speech implementations have been lauded by users;[5][4][6] however, some critics and voice actors have questioned the legality and ethicality of leaving such technology publicly available and readily accessible.[9]

Credited as the impetus behind the popularization of AI voice cloning (also known as audio deepfakes) in content creation and as the first publicly available AI vocal synthesis project to involve the use of existing popular fictional characters[by whom?], 15.ai has a significant impact on multiple Internet fandoms, most notably the My Little Pony: Friendship Is Magic, Team Fortress 2, and SpongeBob SquarePants fandoms. Furthermore, 15.ai has inspired the use of 4chan's Pony Preservation Project in other generative artificial intelligence projects.[10][11]

Several commercial alternatives have spawned with the rising popularity of 15.ai, leading to cases of misattribution and theft. In January 2022, it was discovered that Voiceverse NFT, a company that voice actor Troy Baker announced his partnership with, had plagiarized 15.ai's work as part of their platform.[12][13][14]

In September 2022, a year after its last stable release, 15.ai was temporarily taken down in preparation for a future update. As of November 2024, the website is still offline, with 15's most recent post being dated February 2023.[15]

  1. ^ Kong, Jungil (2020). "HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis". arXiv:2010.05646v2 [cs].
  2. ^ Binkowski, Mikołaj (2019). "High Fidelity Speech Synthesis with Adversarial Networks". arXiv:1909.11646v2 [cs].
  3. ^ Cite error: The named reference deepmind was invoked but never defined (see the help page).
  4. ^ a b Zwiezen, Zack (January 18, 2021). "Website Lets You Make GLaDOS Say Whatever You Want". Kotaku. Archived from the original on January 17, 2021. Retrieved January 18, 2021.
  5. ^ a b Ruppert, Liana (January 18, 2021). "Make Portal's GLaDOS And Other Beloved Characters Say The Weirdest Things With This App". Game Informer. Archived from the original on January 18, 2021. Retrieved January 18, 2021.
  6. ^ a b Clayton, Natalie (January 19, 2021). "Make the cast of TF2 recite old memes with this AI text-to-speech tool". PC Gamer. Archived from the original on January 19, 2021. Retrieved January 19, 2021.
  7. ^ Morton, Lauren (January 18, 2021). "Put words in game characters' mouths with this fascinating text to speech tool". Rock, Paper, Shotgun. Archived from the original on January 18, 2021. Retrieved January 18, 2021.
  8. ^ Ng, Andrew (April 1, 2020). "Voice Cloning for the Masses". The Batch. Archived from the original on August 7, 2020. Retrieved April 5, 2020.
  9. ^ Cite error: The named reference wccftech was invoked but never defined (see the help page).
  10. ^ Cite error: The named reference automaton was invoked but never defined (see the help page).
  11. ^ Cite error: The named reference Denfaminicogamer was invoked but never defined (see the help page).
  12. ^ Williams, Demi (January 18, 2022). "Voiceverse NFT admits to taking voice lines from non-commercial service". NME. Archived from the original on January 18, 2022. Retrieved January 18, 2022.
  13. ^ Wright, Steve (January 17, 2022). "Troy Baker-backed NFT company admits to using content without permission". Stevivor. Archived from the original on January 17, 2022. Retrieved January 17, 2022.
  14. ^ Henry, Joseph (January 18, 2022). "Troy Baker's Partner NFT Company Voiceverse Reportedly Steals Voice Lines From 15.ai". Tech Times. Archived from the original on January 26, 2022. Retrieved February 14, 2022.
  15. ^ @fifteenai (February 23, 2023). "If all goes well, the next update should be the culmination of a year and a half of nonstop work put into a huge number of fixes and major improvements to the algorithm. Just give me a bit more time – it should be worth it" (Tweet) – via Twitter.


Cite error: There are <ref group=lower-alpha> tags or {{efn}} templates on this page, but the references will not show without a {{reflist|group=lower-alpha}} template or {{notelist}} template (see the help page).