ElevenLabs in ClickBait: text to speech
ElevenLabs turns text into speech. ClickBait has three versions of the model: ElevenLabs Multilingual v2, ElevenLabs Turbo v2.5 and ElevenLabs v3. All three share a set of 19 ready voices and take up to 5,000 characters per run. Multilingual v2 and Turbo v2.5 let you set the speaking speed from 0.7 to 1.2. Instead of a ready voice you can paste a voice ID from the public ElevenLabs library.
Updated:
ElevenLabs versions in ClickBait
| Version | Voices | Speed | Text | Features | Price from |
|---|---|---|---|---|---|
| ElevenLabs Multilingual v2 | 19 | 0.7-1.2 | up to 5,000 characters | custom voice ID supported | from 2 tokens |
| ElevenLabs Turbo v2.5 | 19 | 0.7-1.2 | up to 5,000 characters | custom voice ID supported | from 2 tokens |
| ElevenLabs v3 | 19 | up to 5,000 characters | custom voice ID supported | from 2 tokens |
Multilingual v2, Turbo v2.5 or v3
Voices and the text limit are the same in all three versions; the settings differ. Multilingual v2 and Turbo v2.5 have Speed, Stability, Similarity and Style sliders, a Language field and text normalization with auto, on and off. ElevenLabs v3 has one setting: language.
Voices and your own ID
The list has 19 voices: Rachel, Aria, Sarah, Laura, Charlotte, Alice, Matilda, Jessica, Lily, Charlie, George, Callum, Liam, Will, Eric, Chris, Brian, Daniel and Bill. Each name comes with a short note on gender and manner of speech.
Voice not on the list? Choose Custom voice (ID) and paste an ID from the public ElevenLabs library. A clone of your own works only if it is published in the shared library.
How to voice a text with ElevenLabs
Pick a version
In the Voiceover section, open the Engine list and choose ElevenLabs Multilingual v2, Turbo v2.5 or v3.
Paste the text and pick a voice
Up to 5,000 characters at a time, with a counter right above the field. Take a voice from the list or paste your own ID.
Set up and run
Set the speed (on Multilingual v2 and Turbo v2.5) and, if you need to, a language code such as ru or en. The token price is on the Generate voiceover button before you run.
What to do with the finished track
You can play the track right in its card and download it as mp3. Then upload it to Lip sync so the lips in a clip follow the speech, or to Video as an audio reference for Seedance and WAN 3.0.
Where to find it in ClickBait
ElevenLabs lives in ClickBait under the Voiceover section. Sign up, pick a version from the model list and describe what you want to get.
The token price is shown on the run button before you start. If a generation fails, the tokens go back to your balance automatically.
New accounts created with Google or email get a welcome bonus of 10 tokens. These are promo tokens and expire after 14 days.
What you can make with ElevenLabs
AI voiceover
5 models
ElevenLabs, Minimax Speech-02 HD, Seed Audio 1.0
from 2 tokens
Frequently asked questions
Is this the official ElevenLabs website?
No. ClickBait gives you access to ElevenLabs models inside its own service. You do not need an ElevenLabs account, you pay with tokens from one balance, and models for video, images and music sit right next to it.
How much text can I voice at once?
Up to 5,000 characters in any of the three versions. Split a long text into parts and run them one by one.
Can I use my own voice?
Yes, if the voice has an ID in the public ElevenLabs library: choose Custom voice (ID) and paste it. Seed Audio 1.0, another model in the same section, can clone a voice from one to three recordings.
How do I set the language?
Type a language code in the Language field, such as ru or en, or leave the field empty. ClickBait has no fixed list of languages, so check the speech in your language on a short text first.
How is ElevenLabs v3 different from Multilingual v2?
They share voices and limits; the settings differ. Multilingual v2 and Turbo v2.5 have stability, similarity, style and text normalization, v3 only language.
How much does ElevenLabs voiceover cost?
The token price depends on the version and the length of the text and is shown on the button before you run. Each account gets one voiceover at a time; the next ones wait in a queue.