Tool
AI voice changer
eroq changes the voice of a recording: open Voice › Voice changer, record or upload a take, pick a voice (one of 24 roster voices, your clone or a Character's), and it comes back as an MP3 with the same words, timing and delivery in that voice. It costs 4 credits per started minute, on eroq's own GPUs.
40 free credits · no card · private mode on every account
Voice · Conversation
[happy] Good morning! Quick one: the van is booked for nine. [laughing] And whoever is last buys the coffee.
eroq Voice One · My voice
Ready · took 1.2s· −6 credits
[whispering] Hey… are you still up? [sighing] I can't sleep either. I keep replaying tonight. [soft] Okay. Tell me everything, from the start.
eroq Voice One · 3 lines · 2 voices
Ready · took 1.8s· −6 credits
LenaOOrion Speaker
Lena[whispering] Hey… are you still up?
- OOrion
[sighing] I can't sleep either. I keep replaying tonight.
Lena[soft] Okay. Tell me everything, from the start.
- In
- A recording: recorded in the browser or uploaded
- Voices
- 24 roster voices · your clones · your Characters' voices
- Out
- An MP3, same words and timing
- Price
- 4 credits per started minute
- API
- POST /v1/audio/speech with source and voice
How it works
- →1 · Open Voice › Voice changer.
- →2 · Record in the browser, or upload a recording.
- →3 · Pick the voice and generate. The price shows first.
What stays, what changes
Your performance stays: the words, the timing, the pauses, the emphasis. Only the voice changes, so there is no script to type and no line read flat by a text-to-speech engine.
Whose voice
Change recordings you made or have the rights to. Clone only your own voice, or one you have permission to use: imitating a real, identifiable person without their consent is refused.
Clap · AI agent
Or let Clap voice it
Describe the result in Ask. Clap asks what it needs, picks the engines, writes the prompts and prices the plan. Once you approve, it renders everything into your library. Fully automated, and nothing runs before you say yes.
- 1Clap asks one question at a time and keeps the brief, the cast and the storyboard up to date.
- 2The plan lists every render and its price before anything runs.
- 3One click on Approve and everything renders. Failed takes refund themselves.
Ask · Clap
Clap · Thought for 6s
One line per voice, the delivery tags already set. Here is the plan.
Production



Saved to your library
Privacy
Private and unrestricted
- →No filter on eroq's own engines: one written policy instead.
- →They keep nothing, and nothing trains on your work.
- →Private mode keeps no file at all.
Frequently asked questions
How does an AI voice changer work?
You give it a recording and a voice; it says the same thing again in that voice, keeping your timing and delivery. On eroq: Voice › Voice changer, record or upload, pick a voice, generate.
Can I sound like my character?
Yes: give the Character a voice on their page, then pick them in the voice changer. Your take comes back in their voice.
How is it different from text to speech?
Text to speech reads words you type. The voice changer keeps your own performance (where you pause, what you stress) and only swaps the voice.
Can I use it in a live call?
No: it changes a recording. Record the take, then change it.
Is it free?
Free to start: every new account gets 40 free credits with no card, 10 minutes of recording at 4 credits a started minute. A change that fails refunds itself. More credits start with a $10 pack (1,000 credits) or a plan from $15/month.
Try it free
40 free credits · no card · private mode on every account
Keep exploring




