ElevenLabs Studiov3
Lifelike voices and original music, from one text box
Write a script and hear it read by Eleven v3 or Multilingual v2, or describe a track and let Eleven Music compose it.
- Eleven v3 and Multilingual v2 speech
- Music tracks from 5 seconds to 5 minutes
- Every model also available by REST API
Listen before you write a word
Real generations from the models on this page. Each card shows the script or prompt that produced it.
Hey, take a deep breath. You’ve been doing great — even when it doesn’t feel like it. Sometimes, the smallest step forward is still progress.
Hello，welcome to WaveSpeedAI！
High-energy cyberpunk synthwave, driving analog bassline, retro futuristic synthesizers, punchy electronic drums, neon noir atmosphere, 120 BPM, mechanical textures.
I don’t need luck. I need focus. Every move, every second — it all leads to one goal.
Hello, little friend! I am your learning partner, Dr. Bot. Today, we will explore the amazing world of numbers together. Are you ready for a fun adventure? Let's go!
Modern deep house fashion runway music, stylish and elegant, groovy bass, rhythmic hi-hats, vocal chops, luxury brand advertisement vibe, confident and cool.
Meet the future of creativity — powered by AI, designed for humans. This is innovation that speaks in your voice.
Some things define eternity without a single word. They are not a product of time, but a witness to it. This is a classic, born for you—a perfect fusion of craftsmanship and art.
Steampunk ambient atmosphere, ticking clock sounds, mechanical gears clicking, steam hissing, soft acoustic guitar in the background, mysterious and studious.
In a world built on shadows and steel, only one voice can bring the story to life — yours.
Look at this! A golden, crispy crust wrapped around a tender, juicy center—the aroma is simply irresistible. Just one bite, and that rich flavor will melt on your tongue. This is absolutely the best dish I have ever tasted!
Once upon a time, in a forest painted with golden leaves, a little fox discovered that courage often comes wrapped in kindness.
From first line to finished soundtrack, in one studio
1. Voice a script with Eleven v3
Paste narration, dialogue or an ad read, choose a voice by name and get a finished audio file back.
GenerateWelcome to our advanced text-to-speech system! Experience high-quality voice synthesis with natural pronunciation and clear articulation.
2. Speak in more languages with Multilingual v2
The multilingual model reads scripts beyond English with the same voices and controls.
GenerateOh, brilliant. Another 'world-changing' idea, I'm sure. I can barely contain my excitement, really. So, I guess we're all just supposed to start working on this right now, right?
3. Score the moment with Eleven Music
Describe genre, mood, instruments and tempo. Set a length up to five minutes and keep it instrumental, or write lyrics into the prompt for vocals.
GenerateHard Trap, Hip Hop, 808 bass, energetic flow, confident male rap vocals, brass stabs, hype music, motivational sports anthem. [Verse] Laced up tight, ready to go Putting on a major show Sweat and tears on the floor Coming back to get some more [Chorus] Eyes on the prize, reach for the net The greatest game you ever met I take the shot, I make the play Doing this every single day [Outro] Nothing but net. Yeah, we winning.
4. Shape the delivery
Stability and similarity sliders plus a speaker boost switch change how every line is read, without rewriting the script.
5. Or wire it into your product
Each model has its own API endpoint with the same inputs you see here, so a script from your app becomes audio in one request.
View APIPOST /api/v3/elevenlabs/eleven-v3 { "text": "Every setback is fuel.", "voice_id": "Talia", "stability": 0.5 }
Models and pricing
Prices are per generation and update live. Options such as resolution, duration or quality can change the final price, which the generator shows before you run.
| Model | Input | From | |
|---|---|---|---|
| Eleven v3 Text to Speech | Text | $0.20 | Generate |
| Eleven Multilingual v2 Text to Speech | Text | $0.20 | Generate |
| Eleven Music | Prompt | $0.10 | Generate |
Frequently asked questions
Which ElevenLabs speech model should I start with?
Start with Eleven v3, the newest speech model here. Switch to Multilingual v2 when you want to compare voices on a script in another language; both take the same text, voice and settings.
How do I choose a voice?
Type a voice name, such as Talia, Darian or Elowen, in the Voice field of the audio generator. The same names go in the voice_id field when you call the API.
What do stability, similarity and speaker boost do?
They are ElevenLabs voice settings. Stability and similarity each run from 0 to 1 and change how consistent the read is and how closely it follows the chosen voice; speaker boost is an on/off switch. Try a few values on one line to hear the difference.
How long can an Eleven Music track be?
You set the length in the generator, from 5 seconds up to 5 minutes. Tracks are instrumental by default; turn that off and put lyrics in the prompt when you want vocals.
Can I use these models from my own code?
Yes. Every model in the table has an API page with a request example, and the docs cover authentication and fetching results.