When it comes to creating social media posts and podcast episodes, I find myself always having to rerecord different sections. ‘Ums’, ‘Ahs’ and ‘definitely’ are my downfall. Rerecording voiceovers and narrations take time and it can be quite frustrating too. Here’s where TTSMaker comes in. TTSMaker is a completely free AI text-to-speech tool that will save you a lot hassle. It turns your text to speech in a matter of seconds - ideal when your time is limited.
It’s free to use and you don’t need to create an account to use it either. The usage is unlimited, so you can create as many text to speech generations as many times as you want. It also includes commercial usage, which is something I’ve not really seen before for a free tool, normally you would have to pay to get your hands on a commercial usage pack.
TTSMaker is an extremely easy piece of kit to use. Simply add your text into the text box, select your language and desired AI Model voice and click convert to speech. In a few seconds your speech will be ready to download. Before committing to a voice, you can give them a preview, saving you even more time! There are over 60 voice AI models to choose from, so you should find the perfect voice in no time.
When it comes to downloading the speech file, you’re able to download it in a few different formats. These include, mp3, ogg, aac, opus and wav, perfect for whatever you need. The TTSMaker team are constantly working on developing the tool. They do normally offer a free API, but they are currently making changes to it so it isn’t available at the moment - make sure to keep your eyes out for this!
The quality of the voices could be improved, they do seem quite robotic. You are able to switch up the settings slightly in the ‘More setting’ section, even with this it still doesn’t hit the mark for me. But, keep in mind that this tool is completely free and for a free tool, it’s pretty impressive! Depending on your requirements, TTSMaker can take you a long way!