Home

AI Audio · AI voice design

AI Voice Design

Voice design is for when you do not have a donor sample. Type a description — a tired late-night DJ, a bright product host, a low documentary narrator — pick ElevenLabs or Cartesia, and listen. If you like it, save it to Voice Library. If you do not, discard it. Chatterbox cannot design a voice.

Voice design

Design this voice

Describe the voice, pick ElevenLabs or Cartesia, then listen. Save it to Voice Library if you like it, or discard it.

Listen first. Save the ones you like. Discard the rest.

See an example

InfiniteTalk example from Wavespeed. Sample generated by this tool’s model. Your clip uses your photo, script, or prompt.
Voice sample ready to clone
Voice sample ready to clone
Script turned into speech
Script turned into speech
Audio attached to a talking avatar next
Audio attached to a talking avatar next

Why people use AI voice design

Prompt, not a booth

Age, gender, accent, and energy in a sentence. No ten-second sample required.

ElevenLabs or Cartesia

Those two engines design a voice from the prompt. Chatterbox is for cloning and TTS only.

Listen, then keep or discard

Play the preview. Save it to Voice Library if it fits. Discard it if it does not.

Hands off to a face

A saved design is audio identity. Use it later on Text to Speech, talking avatar, or lip sync.

Three simple steps

  1. Step 1: record or upload a sample, or pick a voice
    Step 1

    Describe the voice and pick a model

    ElevenLabs or Cartesia. Be specific: age, accent, pace, and where it will be used.

  2. Step 2: paste the script
    Step 2

    Listen to the preview

    Do not save yet. Hear tone, pitch, and character.

  3. Step 3: generate speech for lip sync
    Step 3

    Save to Voice Library or discard

    Keep the ones you like. Discard the rest. They then work on Text to Speech.

What this clip costs in credits

Every AI voice design job uses the same meter: 150 credits ($1.50) for the first 30 seconds, then 5 credits ($0.05) per extra second. Subscriptions price credits at $0.01; one-time packs are $0.08 each.

DurationcreditsGeneration price
15s150$1.50
30s150$1.50
45s225$2.25
60s300$3.00
90s450$4.50
120s600$6.00

First 30 seconds = 150 credits ($1.50). Plan credits roll over while you stay subscribed.

Good for

Brand narrator

Describe the house voice once, reuse it on every campaign cut.

Character reads

A giant, a child, a noir detective — without hiring a booth.

Localization drafts

Design in English, then generate other scripts in the same identity.

Common questions about AI voice design

You may also like

Each of these is a different job. Use the left menu, or tap one of these cards.