Automate video voiceovers, ad reads, podcasts, and more, in your own voice
![Well, I'll be damned. [laughs] Looks like it's just me and you left. Ain't seen Bodecker since back at Old Ford and... Ah, hell. Let's head back to camp before the dark sets in.](https://elevenlabs.seobdtools.com/__elevenpubliccdn__/payloadcms/mhecc7b6f9-Cowboy Web Asset.webp)
![[ethereal music] Greetings, my friend. What brings you to Mount Olympus today? Here to gaze at my beautiful muscles again?](https://elevenlabs.seobdtools.com/__elevenpubliccdn__/payloadcms/nlox4i4e5fg-Zeus Web Asset.webp)
Generate any AI voice you can imagine using just a text prompt
Customise the tone, accent, age, pacing, and delivery of your voices to create infinite characters with expressive delivery.
Introducing Voice Design, powered by our latest Text to Speech v3 model.
Create lifelike voices from any description - surreal to serious, funny to fierce. Voice any character and bring your stories to life.
Try Voice Design v3
Create any character imaginable with Voice Design v3. Available now on ElevenLabs, free to start.
Sign upA calm, tough and gruff old cowboy with an deep, gravelly, southern American accent.
The friendly mythical God, Zeus, with a huge deep powerful voice. Charming, proud, strong and theatrical.
A calm and husky make warrior with a thick Japanese accent. Soft, whiskery, low tone with a composed and gentle pacing.
A scary old and haggard witch who is sneaky and menacing. She has a croaky, harsh, shrill, high-pitch voice that cackles.
A low, whispery and assertive female voice with a thick French accent. Cool, composed and seductive, with a hint of mystery.
A funny alien from outer space with a ludicrous and annoying voice that always slightly gargles in a silly high-pitch tone.
A very old, cranky and croaky African-American grandma. 80 years old. Very hoarse, grumpy, shrill and frustrated.
Prompt to voice in seconds
Easily customize the voice by choosing age, gender, and pitch. Fine-tune the emotion, delivery, and overall direction. Adjust audio quality and preview your text before generating.
Design the perfect AI voice with our Voice Prompting Guide
Check out our prompting guide for more details on how to produce the best possible voices from Voice Design, and get inspired by sample prompts to help you get started.
Voice Design API
Integrate Voice Design into your product or workflow with our API. We have an endpoint for generating voice previews from a prompt and a separate endpoint for saving those previews to your library. Note: Voice Design with v3 is currently in alpha. It is only available in the dashboard, with API access coming soon.
Voice Design Pricing
Billing
Custom voices
Voice design
Instant voice clones
Professional voice clones
3 voices
Free tier requires attribution and does not have commercial licensing
Elevate your workflow with professional AI tools. Start free today
Create human-like voices with our Text to Speech (TTS) system, built for high-quality narration, gaming, video, and accessibility. Expressive voices, multilingual support, and API integration make it easy to scale from personal projects to enterprise workflows.
Frequently asked questions
Voice Design allows you to create a unique voice from a text prompt by describing the unique characteristics of the voice you need.
Head to Voice -> My Voices -> Add a new voice -> Voice Design.
We created Voice Design to help you fill the gaps when the exact voice they are looking for isn’t available in the Voice Library. Professional Voice Clones are still the highest quality voices on our platform and if there is one available that fits your needs, we recommend using it. But if you can’t find a suitable voice in the Voice Library to fit your vision, use Voice Design.
Voice Design is great for creating character voices like “An angry old pirate, shouting” or “A massive evil ogre, troll” and realistic voices like “A young Indian female with a soft, high voice. Conversational, slow and calm”. Refer to our prompting guide for tips and tricks.
Yes, you can generate new voice previews with this endpoint and save those voices with this endpoint.