We are excited to launch Pro V2 voices, a truly directable text to speech engine with natural language. They can follow complex directions like emotions, speaking speeds, accents and more! Pro V2 is the most expressive set of voices we have launched to date, perfectly delivering your script to life.
Let’s dig in deeper into the capabilities of Pro V2 voices.
To direct the AI Voices, all you need to do is add your directions in square brackets [directions] before your script. We provide a cursory comparison to ElevenLabs as a benchmark.
Non-verbal expressions
[laughing and joking around] hahahaha and he said what haha oooohahahah
Genny Pro V2
ElevenLabs
[sobbing and snorting] gahhhhhhh wahhhhh I’m so sorry, I would have never done this gahhhhh if I knew this will hurt you gahhhhh wahhh
Genny Pro V2
ElevenLabs
Emotions
[super embarassed] Oh my gosh, I am so sorry! I can’t believe I just did that. Please, just pretend that didn’t happen.
Genny Pro V2
ElevenLabs
[slightly angry but obviously annoyed] Seriously? Again? I told you not to do that, and you just keep doing it. I’m at my wit’s end!
Genny Pro V2
ElevenLabs
[extremely happy, on top of the world] YES! This is amazing! I’m so pumped, I feel like I could run a marathon right now! Woohoo!
Genny Pro V2
ElevenLabs
Complex directions: Getting in character and situation
[read like a professor who is super sick and old, wailing, low energy] Healthcare data is highly valuable, and a breach can have far-reaching consequences, both for patients and for the organizations that manage their care. A single breach of sensitive medical information can lead to identity theft, fraud, and in some cases, even blackmail.
Genny Pro V2
ElevenLabs
[speak to injured in a calming way, then shout at someone for help with high energy] Stay still. Don’t move. You’re bleeding badly. But you will be OK, we will get you help. Someone, get a cloth or towel to press on this wound! Call 911!
Genny can do multiple takes for complex directions, much like a real actor would.
Take 1 (more soothing for the injured)
Take 2 (with more energy when calling for help)
ElevenLabs
Accents
Same speaker, different accent directions.
[african american accent] I have a feeling today is going to be a great day. Took a cold shower, put my face in ice carbonated water, rubbed my face with a banana peel, and fought off 100 gorillas!
[british accent] I have a feeling today is going to be a great day. Took a cold shower, put my face in ice carbonated water, rubbed my face with a banana peel, and fought off 100 gorillas!
[korean accent] I have a feeling today is going to be a great day. Took a cold shower, put my face in ice carbonated water, rubbed my face with a banana peel, and fought off 100 gorillas!
(Author’s note: I’m Korean, and I approve that this isn’t racist 😂)
Try it today for free in Genny! Happy Creating.
