Turn your stories into NFTs

0 Following     0 Follower

Text-To-Speech list of AI tools

Here is a list of text-to-speech AI tools, with a few comments about each of their capacities. This will be updated as I find or test new ones.

Voice generation AI services

The following sites are services that you cannot install on your local computers.

  1. ElevenLabs: one of the best text-to-speech system around. With API so you can plug any of your app on it if you want your app to be able to talk. Has instant voice cloning functionality for paid subscribers. (start from $5/month for 30 000 characters / month).
  2. Replicas Studio: AI voice actors for games, film and the metaverse.
  3. Typecast AI: another one.
  4. Murf AI: text to speech.
  5. Speechelo: text-to-speech. More than 30 voices, lots of different languages, you can change tone, pitch, ...

Voice generation AI local tools

Tools that you can run on your local computer or in Google colab notebooks.

  1. TorToiSe: free and open-source. Possibility to clone a voice with 3 to 10 10 second long samples (in WAV format at 22 500 Hz). Notably slow at generating the audio. Only supports English.
  2. Bark: newer than Tortoise, looks very good, with possibility to insert sighs, laughters, ... only has a limited number of voices, and seem to block you from adding new voices. Supports multiple languages. Good YouTube review and tutorial on Bark.
  3. Vall-E: TTS model developped by MicroSoft. Currently not released to the public. It is supposed to be able to clone a voice with only 3 seconds of recording.

Other audio tools

Some tools that can help you get better audio results:

  1. Adobe Podcast Enhancer: a free online tool for enhancing the audio tracks you generated with TTS models. Simply upload your audio file and get it enhanced.

Some news on the topic ...

Just to get some perspective of what is coming up...

  1. Une base de données d'un million d'appels téléphoniques piratée - Capital: this article is in French. 1 million recorded phone calls on sale on the dark web for a few thousand dollars. These calls were recorded by a service provider that made phone calls for some French IAP, banks, postal service, Booking.com, French Railway (SNCF) ...

Yeah, cloned voice Vishing attacks certainly have a bright future... So, beware, don't fall for them.

I'll update this list as soon as I find new tools or services.

Reactions are currently disabled. They will return soon.

⏪ Previous Story

0xedB0...3484 avatar

MetaMask is getting better with NFTs

Beginning of March 2023, I wrote a small tutorial to show you How to see your stories in MetaMask. At the end ...
by 0xedB0...3484

⏩ Next Story

0xedB0...3484 avatar

v0.13.0: from Sequelize to Prisma

After a while working on some other project, here is the new version of StoryPress: absolutely no work on ...
by 0xedB0...3484