Sound like yourself.
IllustrationNo studio session. A short, clean recording of you speaking is enough to clone from.
Creator voiceovers
Your voice on every video without recording each one.
Founder-led ads
The founder's voice, at scale.
Brand voices
One consistent voice across all content.
- Provider
- Resemble AI
- Sample
- 3 to 60 seconds, 10 to 30 seconds of clean speech works best
- Controls
- Expressiveness, pace, temperature
- Seed
- Fixed seed for repeatable reads
- Plans
- Hobby and up
- Cost
- 5 credits per 1,000 characters
What is Chatterbox?
Chatterbox is Resemble AI's voice cloning text to speech model. Upload a sample of one person speaking, between 3 and 60 seconds with 10 to 30 seconds of clean audio working best, and it reads any script in that voice. Expressiveness, pace and temperature controls shape the delivery, and a fixed seed makes reads repeatable. On APImage it costs 5 credits per 1,000 characters, and a cloned voice can also read scripts for Kling Avatar 2 talking videos.
How long does the voice sample need to be?
Between 3 and 60 seconds. A clean 10 to 30 second recording of one person speaking works best.
How much does Chatterbox cost?
5 credits per 1,000 characters.
Can I clone someone else's voice?
Clone your own voice, or one you hold the rights and consent to use. Making a real person appear to say something they did not say is prohibited by APImage's acceptable use policy.
Which plan includes it?
Hobby and up.
How do I use it?
Open the Audio studio, choose Text to speech and pick Chatterbox. Upload a clean 10 to 30 second sample of one person speaking. Write the script and set expressiveness and pace. Generate.