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 generator. Turn a script into a voiceover.
Pick one of 49 voices or your own, and get the voiceover back in any of 85 languages.
Generate a voiceoverFrom $19 a month
Hear this sample read: Audiobook
0:00 / 0:12
Margaret, British, older · Eleven v4
Voices by job.Each one reading a real script.
Every line below is the exact text sent to Eleven v4, tags included. Nothing was edited after.
Product ad
Alexander
Meet Driftwood, the trail shoe that weighs less than your phone. [short pause] Grippy on wet rock, soft on long miles. Wear them for thirty days, or send them back.
0:11
Documentary
William
Every autumn, the salmon return to the river where they hatched. [pause] They swim against the current for weeks. Most of them will not make it home.
0:09
Meditation
Midnight
[quietly] Let your shoulders drop. Breathe in through your nose, slowly. [long pause] And let it go. There is nowhere else you need to be.
0:11
Game character
Rex
[excited] They're through the gate! [shouts] Everyone, to the wall! [laughs] I've waited my whole life for a fight like this. Come on!
0:07
Podcast intro
Harper and Sage
Harper:Welcome back to Small Shop, Big Plans. I'm Harper.
Sage:And I'm Sage. Today, a bakery that sold out its first week [chuckles] without a single ad.0:09
The library has 49 voices, sorted into Ads, Social, Narration, Conversational, Characters and Calm. You can play each one before you pick it.
Direct the read.Write the pauses and laughs into the script.
Tags in square brackets
Put a tag where it should happen. The voice acts it out and doesn't read it. Typing a bracket in the script box lists them.
- Emotion
- [warm] [excited] [curious] [sarcastic] [nervous] [annoyed] [thoughtful] [deadpan]
- Delivery
- [whispers] [shouts] [building] [quietly] [strong French accent]
- Human sounds
- [laughs] [chuckles] [sighs] [exhales] [clears throat] [gulps] [inhales deeply]
- Pauses
- [short pause] [pause] [long pause]
- Sounds
- [applause] [crowd cheering] [door slams]
Several speakers in one file
Add a speaker and write one line per turn. Paste a script written as "NAME: line" and every name becomes a speaker. The podcast intro above is one dialogue with two voices.
- Voices
- Up to 10
- Length
- 2,000 characters across all speakers
- Models
- Eleven v4 and Eleven v3
85 languages.The same voices, in any of them.
Leave Language on Auto and Eleven v4 follows your script. Set it when names, dates or numbers should be read the way one language reads them.
Bienvenidos a Sevilla. Hoy caminamos por el barrio de Santa Cruz, entre patios llenos de flores y calles tan estrechas que casi se tocan.
Welcome to Seville. Today we walk through the Santa Cruz quarter, between patios full of flowers and streets so narrow they almost touch.
0:09
本日もご乗車いただき、ありがとうございます。まもなく東京に到着いたします。お忘れ物のないよう、ご注意ください。
Thank you for riding with us today. We will shortly arrive in Tokyo. Please make sure you have all your belongings.
0:09
Afrikaans, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Belarusian, Bengali, Bosnian, Bulgarian, Burmese, Cantonese, Catalan, Cebuano, Chichewa, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Korean, Kyrgyz, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Occitan, Odia, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Serbian, Sindhi, Slovak, Slovenian, Somali, Spanish, Swahili, Swedish, Tajik, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Yoruba
Every language Eleven v4 reads
- Afrikaans
- Arabic
- Armenian
- Assamese
- Asturian
- Azerbaijani
- Belarusian
- Bengali
- Bosnian
- Bulgarian
- Burmese
- Cantonese
- Catalan
- Cebuano
- Chichewa
- Chinese
- Croatian
- Czech
- Danish
- Dutch
- English
- Estonian
- Filipino
- Finnish
- French
- Galician
- Georgian
- German
- Greek
- Gujarati
- Hausa
- Hebrew
- Hindi
- Hungarian
- Icelandic
- Indonesian
- Irish
- Italian
- Japanese
- Javanese
- Kannada
- Kazakh
- Korean
- Kyrgyz
- Latvian
- Lingala
- Lithuanian
- Luxembourgish
- Macedonian
- Malay
- Malayalam
- Maltese
- Maori
- Marathi
- Mongolian
- Nepali
- Norwegian
- Occitan
- Odia
- Pashto
- Persian
- Polish
- Portuguese
- Punjabi
- Romanian
- Russian
- Serbian
- Sindhi
- Slovak
- Slovenian
- Somali
- Spanish
- Swahili
- Swedish
- Tajik
- Tamil
- Telugu
- Thai
- Turkish
- Ukrainian
- Urdu
- Uzbek
- Vietnamese
- Welsh
- Yoruba
Make your own voice.Record it, upload it, or describe it.
A voice you make works on Eleven v4, every other ElevenLabs model, Qwen 3 and Seed Audio. Link it to a Persona and it becomes that Persona's voice.
Record yourself
Read a short script out loud in the browser. A minute of speech gives the closest copy.
Upload a clip
An MP3, WAV or M4A with at least 10 seconds of one person talking. Longer clips open trimmed to 5 minutes, and a switch removes background music.
Describe a voice
Write how it should sound, such as an older man with a warm Scottish accent. Three options read your line, and you keep one.
From voice to video.The voiceover doesn't have to stay audio.
- Narrate a whole video with StorybookType a topic. Storybook writes the script, illustrates it, and narrates it with the same voice library, in 73 languages.10 seconds to 5 minutes
- Put the voice on a face with Lip syncLip sync matches a face's mouth to speech. Write the line in its audio field and it generates the voiceover there, or upload the MP3 you made here.Up to 5 minutes of audio
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
AI voice generator FAQ
Plans start at $19 a month. That covers about 1.5 hours of voiceover. Eleven v4 costs 4 credits per 1,000 characters, which took about 66 seconds to read in the samples on this page. Eleven v4 Turbo costs 3, but it can't read a dialogue with several speakers. You can play every read on this page without an account.
It reads written text out loud in a synthetic voice. You paste a script, pick a voice, and get an audio file back. In Sceneform that happens in the Voiceover tab of Audio.
The library has 49 voices, grouped as Ads, Social, Narration, Conversational, Characters and Calm. You can play each one before you pick it. Voices you make yourself sit at the top of the list.
Yes. Record yourself for about a minute, or upload a clip of at least 10 seconds. You can also describe a voice and pick one of three designs.
On Eleven v4, write a tag in square brackets where you want it, such as [whispers], [laughs] or [long pause]. The voice acts the tag out and doesn't read it. The script box offers the tags as you type a bracket.
Eleven v4 reads 85 languages. Leave Language on Auto and it follows your script. Other voice models in Audio cover fewer.
Up to 10,000 characters in one generation on Eleven v4. A dialogue with several speakers can be 2,000 characters.
Yes. Every paid plan includes commercial use of what you make. Download the voiceover as an MP3, or use it in Sceneform's video tools.
Not with these voices. They speak. For a song with vocals, describe the genre, mood and lyrics in Sceneform's AI music generator.
Spell the name the way it sounds, then generate again. If the script mixes languages, set Language to the one the names and numbers belong to.