AI voiceover
To turn text into speech, paste it into the Voiceover section and pick a model and a voice. There are 45 ready voices across three families: ElevenLabs (Multilingual v2, Turbo v2.5 and v3 share one set), Minimax Speech-02 HD, and Seed Audio 1.0. Seed Audio clones a voice from 1-3 recordings and makes sound effects from a description, and Minimax offers eight emotions.
Updated:
Voiceover models and their settings
| Version | Developer | Voices | Speed | Text | Features | Price from |
|---|---|---|---|---|---|---|
| ElevenLabs Multilingual v2 | ElevenLabs | 19 | 0.7-1.2 | up to 5,000 characters | custom voice ID supported | from 2 tokens |
| ElevenLabs Turbo v2.5 | ElevenLabs | 19 | 0.7-1.2 | up to 5,000 characters | custom voice ID supported | from 2 tokens |
| ElevenLabs v3 | ElevenLabs | 19 | up to 5,000 characters | custom voice ID supported | from 2 tokens | |
| Minimax Speech-02 HD | MiniMax | 6 | 0.5-2 | up to 5,000 characters | 8 emotions to choose from | from 2 tokens |
| Seed Audio 1.0 | ByteDance | 20 | 0.5-2 | up to 2,048 characters | clones a voice from 1 to 3 recordings; makes sound effects and ambience from a description; up to 48 kHz | from 2 tokens |
How to voice a text
Paste the text
Up to 5,000 characters at a time, or 2,048 on Seed Audio.
Pick a voice
A ready voice from the list, your own voice ID in the ElevenLabs models, or a recording to clone in Seed Audio.
Set up and run
Speed, emotion, language: the settings depend on the model. The token price is on the button.
Voice cloning and several speakers
Seed Audio 1.0 copies a voice from a clean 10-30 second recording, and you can upload up to three of them. In the text, lines are tied to the recordings with the tags @Audio1, @Audio2 and @Audio3, so one track can have several speakers.
Sound effects, speed and emotions
Seed Audio has a sound generation mode: describe a scene, such as street noise or rain outside a window, and you get a track without speech at up to 48 kHz.
Every model except ElevenLabs v3 lets you change the speaking speed: 0.7 to 1.2 on ElevenLabs Multilingual v2 and Turbo v2.5, 0.5 to 2 on Minimax and Seed Audio. Minimax Speech-02 HD has eight emotion options. ElevenLabs and Minimax have a Language field: leave it on auto or type the language yourself, as a code such as ru or en on ElevenLabs.
Where to find it in ClickBait
AI voiceover 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.
Models for this task
ElevenLabs
text to speech up to 5,000 characters, 19 voices
from 2 tokens
Other tools
AI video generator
12 models
Kling, Seedance, Veo, WAN, MiniMax H3
from 8 tokens
Image to video
13 models
Kling, Kling Motion Control, Seedance, Veo, WAN, MiniMax H3
from 8 tokens
AI image generator
18 models
Kling, Nano Banana, GPT Image, Seedream, FLUX, WAN, Z-Image
from 2 tokens
Lip sync
5 models
Lipsync 2, Lipsync 2 Pro, Lipsync 3, InfiniteTalk, LatentSync
from 4 tokens
AI music generator
9 models
Suno
from 5 tokens
Video upscaler
1 model
Upscale
from 2 tokens
AI UGC video
12 models
Kling, Seedance, Veo, WAN, MiniMax H3
from 8 tokens
Product ad video
12 models
Kling, Seedance, Veo, WAN, MiniMax H3
from 8 tokens
Creatives for affiliate marketing
30 models
Kling, Seedance, Veo, Nano Banana, GPT Image, Seedream, FLUX, WAN, MiniMax H3, Z-Image
from 2 tokens
Marketplace product photos
17 models
Kling, Nano Banana, GPT Image, Seedream, FLUX, WAN
from 2 tokens
Videos for TikTok and Reels
12 models
Kling, Seedance, Veo, WAN, MiniMax H3
from 8 tokens
Ad posters and banners
17 models
Kling, Nano Banana, GPT Image, Seedream, FLUX, WAN, Z-Image
from 2 tokens
Frequently asked questions
Can I clone a voice?
Yes, in Seed Audio 1.0. Upload a clean 10-30 second recording of the voice and write the text you want spoken.
How much text can I voice at once?
Up to 5,000 characters in the ElevenLabs and Minimax models, up to 2,048 in Seed Audio. Split long texts into parts.
Can I choose an emotion?
Yes, Minimax Speech-02 HD has eight emotion options. In ElevenLabs Multilingual v2 and Turbo v2.5, stability and style sliders change the delivery.
Can I have several speakers?
Yes, in Seed Audio 1.0: upload up to three voice recordings and mark who speaks in the text with @Audio1, @Audio2 and @Audio3.
Can I generate sound effects and ambience?
Yes, with the sound generation mode in Seed Audio 1.0. Describe what it should sound like and you get a track without speech.
How much does a voiceover cost?
The token price depends on the model and the length of the text and is shown on the button before you run. You get one voiceover at a time; the next ones wait in a queue.