🤖AI Text-to-Speech

Getting Started

To use KickBot TTS, you will need a KickBot account. If you do not already have one, you can sign up at KickBot.com. For setup guidance, follow this guide.

By default, every KickBot user has access to 4 free TTS voices (male, female, TikTok, and Brian). Premium users unlock 2,000+ ultra-realistic voices including celebrities, characters, streamers, and more, plus 10 custom voice clone slots to replicate any voice.

To get started, go to "TTS Commands" page in the TTS section of your left sidebar.

Commands List

You will first see all the TTS commands configured for your channel. On this page you have the ability to edit each command, adjust the permissions, and turn the command on or off.

Voice Library

The voice library lets you discover thousands of AI voices created by KickBot and the community. Voices are sorted by most to least popular, you can also view trending voices and newly created voices. To add a voice to your channel, press the + button next to the voice. It will then be added to your command list. There is no limit on the number of voices you can add.

Moderation

Automatically moderate TTS messages using powerful AI and custom filters. AI filters automatically detect and block inappropriate TTS messages across multiple categories. You can also set up custom banned words, block specific users from TTS, and create regex patterns to filter things like phone numbers or emails.

TTS Settings

In this module there are settings which globally apply to TTS.

These settings are:

• TTS Enabled: Toggles TTS playback on or off, by default this is set to on.

• Automatic TTS: Reads every message in chat with TTS. This is not affected by cooldowns.

• Read sender name: Reads the message senders name as well as their message.

• Delay: Adds a delay between TTS messages.

• User Cooldown: The minimum amount of time each viewer must wait until they can send a TTS message.

• Global Cooldown: The minimum amount of time between any TTS message (this applies to viewers, streamers and mods).

• Max Characters: The maximum length of a TTS message.

• TTS Volume: The volume of TTS messages.

• On Screen Preview: Show a preview of the TTS message on stream through the browser source.

• Voice List: An easy to access page where viewers can see a full list of your TTS commands.

In addition to the above, there are "chat commands" which can adjust TTS settings while streaming, these commands are:

• !ttsoff Disables TTS. Any remaining messages in the queue will still be played.

• !ttson Enables TTS.

• !ttsclear Clears the queue. This does not stop any active TTS playback.

• !ttsskip Stops active TTS playback.

• !ttsvol 0-100 Adjusts the TTS volume. Requires a volume parameter between 0-100.

• !ttsdelay 0-30 Adjust the TTS delay. Requires seconds parameter between 0-30.

Voice Cloning

Create custom AI voices from short audio clips for use on your stream. Voice cloning requires 30-90 seconds of clean, high-quality audio featuring one person speaking clearly. The clearer the audio with minimal background noise, the better your AI voice will sound. Voice cloning can be accessed under the "Commands" section.

After clicking "Add Voice" you will need to enter the following information:

• Voice name: The publicly shown name of the voice.

• Default command: The default command that will be used to trigger this voice.

• Voice icon: A publicly shown icon representing the voice.

• Audio samples: Up to 90 seconds of audio that will be used to create the voice. Multiple files are supported with a 10MB limit

Voice training can take up to a minute - don't close or refresh the page during this process. After creation, you will see the voice in your command list. If you selected for the voice to be made public, this triggers a manual review process to ensure quality, usually completed within 1-2 business days. You will receive an email when it is made public.

Widget URL

In order to enable TTS in your streaming, you need to add a custom URL to as a browser source in your streaming software. This widget URL can be found on the TTS settings page.

Adding the Browser Source

1. Copy the widget URL .

2. Add a browser source to your OBS scene.

3. Paste the widget URL into the box labeled "URL".

4. Enable "Control audio via OBS".

5. Click "OK".

Enabling Audio Monitoring

Based on your OBS setup, enabling audio monitoring for the TTS browser source may be necessary. Achieve this through the following steps:

1. Access the TTS advanced audio properties in the audio mixer (click the 3 dots next to the TTS volume slider).

2. Set audio monitoring to "Monitor and Output".

3. (Optional) Go to your OBS settings, go to "Audio", and in the advanced section ensure the monitoring device is set to a device you can hear. The default option is recommended for most users.

Using the TTS Command

Open your Kick chat and type the command prefix, followed by the text you want to be read aloud. Shortly after, you should hear the message read through OBS.

FAQs