Skip to main content

How to use voice in Character.AI

Character.AI homepage with voice highlight.
Character.AI

The Character.AI chatbot service includes several features to optimize your AI communication experience. The primary function of Character.AI is a text-to-speech chatbot that allows you to type queries and read responses from various characters including modern and historical figures, popular fictional characters, and helpful personas, among others. However, you can also implement a voice feature that allows you to listen to responses from the characters in a human-like voice. This can work as an accessibility option, or if you simply don’t feel like reading your responses.

Character.AI allows you to enable voice options on the third-party characters you’re interacting with and also lets you upload custom voices for characters on your own account. Here are the ins and outs of working with voices on Character.AI.

Recommended Videos
Enable Character.AI voice on a third-party character.
Character.AI

How to enable voice on a third-party character

As said, the enabled voice feature on Character.AI allows you to hear a character’s voice when it responds to your comment or query in a conversation. Say you are chatting with a Super Mario character that might resemble the famous plumber with voice-enabled.

Step 1: To turn on the voice feature for a third-party character chat, open a chat and click the sound icon that looks like sound lines with a slash crossed through.

This will automatically enable voice, and the icon will turn blue. You will also see a voice-enabled notice pop up and quickly disappear.

Step 2: Alternatively, you can click the three-dot icon to the right of the sound icon. In the drop-down menu, hover over the sound icon — and it will read Turn sound on.

Step 3: Click the icon, and it will enable voice from there.

Create a custom Character.AI voice.
Character.AI

How to create a custom voice

To create your own voice sound on Character.AI, you will need to upload a clear audio clip between 10 and 15 seconds. So start off by getting that ready.

The service will use this clip to train the algorithm so that characters will be able to respond in detail based on that short sound. You can preview the voice again, but now it will be cut down to about three seconds based on your intro and processed to sound a bit cleaner and more bot-like.

Step 1: Once you’ve customized your settings, click Create Voice. If you choose to make your voice public, you’ll receive an extra confirmation notice, click Confirm and the voice will be available for use. Click Done and you’ll see the voice in the voices section of your public profile.

From here, you’ll be able to add the voice to any new characters you make. If you made the voice public, it will be available among the Character.AI community for others to use for their characters.

If you ever want to delete the voice, you can select it in your public profile, click Edit, and Delete.

Step 2: To start off, click Create on the Character.AI home tab and then click Voice.

Step 3: This will take you to the Create Voice page, where you can drag and drop your clip or click Upload to select your audio from your computer files. Your raw sound will automatically upload, and you’ll have the opportunity to preview and reupload it if there are any issues.

If not, you can then click Generate Voice.

Step 4: The next page is a New Voice settings page, where you can input details about your voice, including an intro, a voice name, and a description. There is also an option to make your voice public.

Add a voice to a new Character.AI character.
Character.AI

How to add a voice to a new character

Including a voice is necessary to create a character in Character.AI, so the steps to do so are simple.

Step 1: Click Create on the Character.AI home tab and then click Character. This will take you to the new character page where you fill in all of the details necessary for a new Character.AI character, including name, tagline, description, greeting, and definition.

Step 2: When you get to voice, click Add and a box with voice options will pop up. You can scroll or search through voice options in the Discover tab.

Step 3: Switch to the Your Voices tab to search through any voices you’ve created. Hover over the voice you want and click Select.

Step 4: Fill in the rest of the settings information and then click Create Character to complete the process.

Step 5: Once your new character is live, you can interact with it just like a third-party chat in your account and enable voices to hear your custom voices on your own chat.

Fionna Agomuoh
Fionna Agomuoh is a Computing Writer at Digital Trends. She covers a range of topics in the computing space, including…
OpenAI teases its ‘breakthrough’ next-generation o3 reasoning model
Sam Altman describing the o3 model's capabilities

For the finale of its 12 Days of OpenAI livestream event, CEO Sam Altman revealed its next foundation model, and successor to the recently announced o1 family of reasoning AIs, dubbed o3 and 03-mini.

And no, you aren't going crazy -- OpenAI skipped right over o2, apparently to avoid infringing on the copyright of British telecom provider O2.

Read more
Ray-Ban Meta Smart Glasses get real-time visual AI and translation
Tracey Truly shows multi-reflective options with Ray-Ban Meta Smart Glasses.

Meta is rolling out two long-awaited features to its popular Ray-Ban Smart Glasses: real-time visual AI and translation. While it's just being rolled out for testing right now, the plan is that, eventually, anyone that owns Ray-Ban Meta Smart Glasses will get a live assistant that can see, hear, and translate Spanish, French, and Italian.

It's part of the v11 update that cover the upgrades Meta described at its Connect 2024 event, which also include Shazam integration for music recognition. This all happens via the camera, speakers, and microphones built into the Ray-Ban Meta glasses, so you don’t need to hold up your phone.

Read more
OpenAI opens up developer access to the full o1 reasoning model
The openAI o1 logo

On the ninth day of OpenAI's holiday press blitz, the company announced that it is releasing the full version of its o1 reasoning model to select developers through the company's API. Until Tuesday's news, devs could only access the less-capable o1-preview model.

According to the company, the full o1 model will begin rolling out to folks in OpenAI's "Tier 5" developer category. Those are users that have had an account for more than a month and who spend at least $1,000 with the company. The new service is especially pricey for users (on account of the added compute resources o1 requires), costing $15 for every (roughly) 750,000 words analyzed and $60 for every (roughly) 750,000 words generated by the model. That's three to four times the cost of performing the same tasks with GPT-4o.

Read more