Creator
$19/month
Billed monthly
For solo creators posting every week
500 credits every month
- Up to 250 AI images
- Up to 50 AI videos
- Up to 1.5 hours of AI voiceover
- Roll over up to 1,000 credits
AI voice cloning
Your voice, reading anything you type.
Record yourself for a minute, or upload a clip of at least 10 seconds. Sceneform makes a voice from it that reads any script, in 85 languages.
Clone your voiceMaking the voice is free. Reading scripts in it needs a plan, from $19 a month.
0:59
The house had been empty for eleven years. [pause] Nobody had told the clocks.
0:06
How much audio do you need?Ten seconds is the minimum. A minute is best.
The sample reads the script the Record step gives you. Each mark is where a shorter sample would stop. The voice made from everything before a mark reads a new line.
10 s31 s
Each voice reads “The house had been empty for eleven years. [pause] Nobody had told the clocks.”
10 sminimum
0:0631 sgood
0:0659 sbest
0:06
The Record step's meter marks the same three lengths. Uploads longer than 5 minutes are trimmed to 5.
Three ways in.Record, upload, or describe.
Open Create voice in Audio. Record in the browser, upload a recording, or describe a voice and hear three designs.
1
Record yourself
Read in the browser for about a minute. The dialog gives you a script, and it doesn't have to be word for word.
Your voice reads a new line
“The house had been empty for eleven years. Nobody had told the clocks.”
2
Upload a clip
An MP3, WAV or M4A with at least 10 seconds of one person talking. Up to 5 minutes is used, and a switch removes background music.
Choose the clearest section of one person speaking.
3
Describe a voice
Write how it should sound and a line to test it with. Three options read the line, and you keep one.
Description
“A woman in her thirties with a warm, low voice and a light Scottish accent. Relaxed and friendly, speaking at an easy, natural pace, recorded close to the microphone in a quiet room.”
- Option 1Kept
- Option 2
- Option 3
Option 1 became the sample at the top of this page.
- Option 1
How to clone your voicein four steps.
Voice cloning learns how one person sounds from a recording of them talking. Then it reads new text in that voice.
- 1
Open Create voice
In Audio, open the voice menu or the Voices tab and choose Create voice.
- 2
Record or upload
Record about a minute of speech, or upload a clip of at least 10 seconds.
- 3
Name it and save
Sceneform checks the sample and makes the voice. It shows under Yours in the voice picker.
- 4
Type a script
Pick Eleven v4, write what the voice should say, and generate. Download it as an MP3.
Where your voice goes.Voiceovers, Personas and faces.
Your voices work on every ElevenLabs model in Audio, on Qwen 3, and on Seed Audio, which copies the first 30 seconds of the sample.
- Voiceovers and dialogueRead ads, narration and scripts with several speakers on Eleven v4 or Eleven v3. Your voices sit next to the library's.
- A Persona's voiceMake it a Persona's default voice. Picking the Persona then picks the voice too.
- A face that speaks itRead a line in your voice, then give the MP3 to Lip sync. It matches a face's mouth to the speech.
Simple pricing that scales with you.
Pick the plan for how much you post. Every model on every plan. Unused credits roll over. Cancel anytime.
Pro
Most popular$49/month
Billed monthly
For creators posting daily across channels
1,300 credits every month
- Up to 650 AI images
- Up to 130 AI videos
- Up to 4 hours of AI voiceover
- Roll over up to 2,600 credits
Studio
$99/month
Billed monthly
For brands and production teams
2,700 credits every month
- Up to 1,350 AI images
- Up to 270 AI videos
- Up to 9 hours of AI voiceover
- Roll over up to 5,400 credits
Scale
$199/month
Billed monthly
For agencies running always-on content
5,500 credits every month
- Up to 2,750 AI images
- Up to 550 AI videos
- Up to 18 hours of AI voiceover
- Roll over up to 11,000 credits
Every plan includesEvery model, 90+ and countingReusable AI personasSceneform Studio editorCommercial usage rights
Want checkout, comparison tables, or a custom volume? See the full pricing page
Before you recordVoice cloning questions
Making the voice is free. Reading a script in it uses credits, and credits come with a paid plan, from $19 a month. That plan covers about 1.5 hours of speech. Eleven v4 costs 4 credits per 1,000 characters.
At least 10 seconds of one person talking. Thirty seconds is better, and a minute is best. Longer uploads are trimmed to 5 minutes.
Close, not identical. Play the sample at the top of this page next to the voice made from it to hear the gap. Record in a quiet room, alone, at your normal pace.
A model learns how one person sounds from a recording of them talking. Then it reads new text in that voice, including words the person never said.
Keep up to 10 custom voices in your account. They appear under Yours in the voice picker. Deleting a voice also deletes its sample.
Yes. On Eleven v4 it reads 85 languages, and Qwen 3 reads 10. Leave Language on Auto and the model follows your script. The Spanish line at the top of this page is one example.
No. Cloned voices speak. For a song with vocals, describe the genre, mood and lyrics in Sceneform's AI music generator.
Yes. Every paid plan includes commercial use of what you make. Download the read as an MP3, or use it in Sceneform's video tools.