AI Voice Changer: Same Words, New Voice
Updated
Short answer: VdoBloom AI Voice Changer takes up to 30 seconds of your own speech and re-speaks the same words in a different voice. Pick one of 12 target voices (deep male, soft female, documentary narrator, radio host, whisper, robot, cartoon character and more) or describe the voice you want. It runs on ByteDance Seed Audio 1.0.
A run costs about 0.21 credits per second of your recording (rounded up per run, 1 credit minimum) plus 6 credits to transcribe it, or nothing extra if you type what the recording says. A 10-second clip with typed words costs 3 credits; a 30-second clip transcribed for you costs 13.
You must confirm the voice is yours or that you have the speaker's permission. Imitating celebrities, public figures or anyone who has not agreed is not allowed.
How it works
- 1
Record or upload your speech
Record up to 30 seconds in the browser (it stops by itself) or upload a clip. One speaker, clear speech, little background noise.
- 2
Choose the target voice
Tap one of the 12 preset voices, or type a short description such as "a raspy old pirate". Adjust the pitch if you like.
- 3
Optionally type what you said
Typing the exact words skips automatic transcription and its 6-credit charge.
- 4
Confirm consent and change the voice
Tick the consent box, check the price above the button and press Change Voice. The result plays on the page and is saved to My Creations.
Quick facts
- Input
- Up to 30 seconds of speech, recorded in the browser or uploaded (max 25 MB)
- Target voices
- 12 presets, or your own description (up to 300 characters)
- Pitch
- -12 to +12 semitones
- Price
- About 0.21 credits per second (rounded up per run) + 6 credits for transcription, or + 0 if you type the words
- Output
- MP3, saved to My Creations
- Consent
- Required on every run and stored with the job
- If it fails
- Credits are refunded automatically
| AI Voice Changer | |
|---|---|
| Input | Up to 30 seconds of speech, recorded in the browser or uploaded (max 25 MB) |
| Target voices | 12 presets, or your own description (up to 300 characters) |
| Pitch | -12 to +12 semitones |
| Price | About 0.21 credits per second (rounded up per run) + 6 credits for transcription, or + 0 if you type the words |
| Output | MP3, saved to My Creations |
| Consent | Required on every run and stored with the job |
| If it fails | Credits are refunded automatically |
How much does it cost?
The price is shown before you start and is the same number that is charged.
- 10 s clip, words typed
- 3
- 10 s clip, auto-transcribed
- 9
- 30 s clip, words typed
- 7
- 30 s clip, auto-transcribed
- 13
| Run | Credits |
|---|---|
| 10 s clip, words typed | 3 |
| 10 s clip, auto-transcribed | 9 |
| 30 s clip, words typed | 7 |
| 30 s clip, auto-transcribed | 13 |
Read more: Credit packs and plans
Voice Changer, Voice Clone or Voice Design?
Voice Changer keeps your words and performance and swaps the voice. Voice Clone makes your own voice read new text. Voice Design invents a voice from a description and reads text you type.
Read more: AI Voice Clone · Voice Design
Frequently asked questions
How long can my recording be?
Up to 30 seconds per run. Split longer recordings into parts.
Will it keep my words exactly?
It is asked to keep the same words, pacing and emotion. Typing the exact words yourself gives the closest result, especially for names or jargon.
Can I make myself sound like a celebrity?
No. Imitating celebrities, public figures or anyone without their consent is against the Terms of Service.
Why is there a 6-credit transcription charge?
The model needs the words you said. Leave the box empty and we transcribe the clip for 6 credits; type them yourself and it costs nothing extra.
What happens if a run fails?
The job is marked failed and its credits are refunded automatically.