Short instructions

Here's what to do: Select a provider, voice, and phrase, then click the 'Speak!' button. Repeat. Try to find the voice you like best.

The Story

Initially, I wanted to compare voices from several major text-to-speech services: Elevenlabs, OpenAI, Google WaveNet, Amazon Polly and Microsoft. While all of them offer pages to sample their synthetic voices, these samples are often deeply buried within technical examples of their APIs.

So, I decided to create a one-stop, easy comparison of all of them. I compiled a set of text snippets that imitate commonly used topics for voiceovers, and created audio files where these texts are read by all the voices.

Eventually, I thought, why stop here? So, I added recordings from actual voiceover artists to the comparison. Now, you can compare synthesized voices with real human voices to get a firsthand feel for the current state of text-to-speech technology.

Also, when you are done playing with pre-defined samples and are ready to read out your own text,
check out our free voice generator !