Text to your own speech.
The voice of AI generation.

Text-to-Speech (TTS) is technology that uses artificial intelligence (AI) to generate audio from written text. TTS allows you to transform digital copy into audio that’s read out loud by an AI-generated voice.

It works on most devices-computers, smartphones, and tablets. And it can typically process most common file formats, like Word, PDF, MOBI, HTML, and even web pages or images.

You have some level of flexibility with the generated voices, like adjusting gender, speed or accent. Rapid developments in TTS over the past years means these voices can sound way more natural than ever before.

The most common use cases include: audiobooks, education (e.g. teaching children how to read), accessibility (e.g. assisting people with visual impairment), business (e.g. customer support), and even traveling (text to speech apps to facilitate communication abroad).

AI voice is the technology that produces a voice replicating a real person's voice. 

To do so, AI voice takes samples of a person's speech (usually voice recordings) to create a voice that sounds like them. 

Nowadays, the accuracy of a cloned voice can be impressive. This applies not only to how the voice sounds, but also to being able to replicate a specific person’s speech patterns and characteristics, like intonation, accent and more. 

Riverside’s AI Voice uses an advanced AI voice cloning model. It allows you to replicate your own voice with the highest levels of accuracy.

There are 3 key stages when cloning your voice with Riverside’s AI: Sampling, adding your text, generating. It is fast and simple.
 
You simply click the “AI Voice” button in your studio and add in your text in the pop-up window. This can be up to 2,000 characters at a time and in any of the 100+ languages Riverside supports.

Once finished, you simply click the “Generate AI Voice” button and within seconds your new audio recording gets added to your studio. 

You can work with the file as you typically do on Riverside: Open to edit in the Riverside editor, download or share.

No. You can only reproduce your own voice, provided that you’re the account owner and that you opted to generate your voice clone. 

You can’t use AI Voice by RIverside to generate the voices of your guests, producers or anyone else (that includes Spongebob’s voice, for example). 

This is why you can’t generate voices from uploaded media. You can only use this feature for recordings you make in your studio, while being logged in with your credentials. 

Our technology samples your voice based on your last two recordings. 

While different laws and restrictions may apply in different locations, cloning another person’s voice without an agreement or their explicit consent can infringe their privacy rights. 

Depending on how the cloned voice is used, there may also be grounds for violation of laws around fraud, intellectual property, impersonation and more. 

Riverside doesn’t facilitate, permit or in any other way facilitate voice cloning for anyone else other than the person holding a paid account. 

Even in this case, the account owner must explicitly request that their voice is cloned. There is a stringent process in place to authenticate the account owner's voice.

You must have a Pro or Business account with Riverside to get access to this feature. Only the account owner can use it to clone their voice.

You can input up to 2,000 characters maximum each time you use AI Voice, and up to 5,000 characters per month. 

You get a studio-quality recording with AI Voice (same as with every recording on Riverside!). The audio file is 4.1Khz.
‍
And as far as how realistic your cloned voice sounds… we bet you even those closest to you won’t be able to tell the difference.

Riverside’s AI Voice uses the last two recordings in your account to sample your voice. Meaning we sample your voice and model its clone based not only on what your voice sounds like, but also other speech characteristics that are unique to you. Like your intonation, how you pronounce certain letters or sounds, or how you pitch or lower your voice naturally to convey emotions.