ElevenLabs

The AI voice platform behind Eleven v3: speech with audio tags, voice design and cloning, sound effects, music and dubbing. A free masterclass with ElevenLabs' own scripts, most of which run right here in the Lab.

What it nails

• Eleven v3 performs with laughs, whispers and accents
• Voices, sound effects and music in one place
• Most tools run in the Lab by the run

Watch out for

• Free plan has no commercial licence

ElevenLabs calls its Eleven v3 model "the most expressive Text to Speech model". Eleven v3 (out of alpha on 2 February 2026) does not just read text, it performs: it laughs, whispers, sighs, switches accents and even sings when you ask with simple audio tags. Around it: Voice Design, voice cloning, a voice changer, sound effects, Eleven Music, dubbing into 90+ languages, and speech-to-text.

Most of these run in the Lab's Audio studio: Text to Speech (Eleven v3, Multilingual v2, Flash v2.5), Voice Cloning, Speech to Speech, Sound Effects and Music. Every ElevenLabs script below with a green button opens there, ready to generate.

Start here: pick the right model

Lesson 1: make v3 act with audio tags

Write tags in square brackets right where the emotion or sound should happen.

• The voice matters most. A shouting voice will not whisper well, and a serious narrator may ignore [giggles]. Match tags to the voice.
• Set Stability: Creative is "more emotional and expressive, but prone to hallucinations"; Natural is "balanced and neutral"; Robust is "highly stable, but less responsive to directional prompts".
• Combine tags freely; many undocumented tags work too.
• Stuck? The Enhance button adds tags for you.

Okay, you are NOT going to believe this.

You know how I've been totally stuck on that short story?

Like, staring at the screen for HOURS, just... nothing?

[frustrated sigh] I was seriously about to just trash the whole thing. Start over.

Give up, probably. But then!

Last night, I was just doodling, not even thinking about it, right?

And this one little phrase popped into my head. Just... completely out of the blue.

And it wasn't even for the story, initially.

But then I typed it out, just to see. And it was like... the FLOODGATES opened!

Suddenly, I knew exactly where the character needed to go, what the ending had to be...

It all just CLICKED. [happy gasp] I stayed up till, like, 3 AM, just typing like a maniac.

Didn't even stop for coffee! [laughs] And it's... it's GOOD! Like, really good.

It feels so... complete now, you know? Like it finally has a soul.

I am so incredibly PUMPED to finish editing it now.

It went from feeling like a chore to feeling like... MAGIC. Seriously, I'm still buzzing!

Example by ElevenLabs · source ↗ · Runs in the Lab: this button opens the Audio studio. Pick the Eleven v3 model for audio tags.

[professional] "Thank you for calling Tech Solutions. My name is Sarah, how can I help you today?"

[sympathetic] "Oh no, I'm really sorry to hear you're having trouble with your new device. That sounds frustrating."

[questioning] "Okay, could you tell me a little more about what you're seeing on the screen?"

[reassuring] "Alright, based on what you're describing, it sounds like a software glitch. We can definitely walk through some troubleshooting steps to try and fix that."

Example by ElevenLabs · source ↗ · Runs in the Lab: this button opens the Audio studio. Pick the Eleven v3 model for audio tags.

[laughs] Alright...guys - guys. Seriously.

[exhales] Can you believe just how - realistic - this sounds now?

[laughing hysterically] I mean OH MY GOD...it's so good.

Like you could never do this with the old model.

For example [pauses] could you switch my accent in the old model?

[dismissive] didn't think so. [excited] but you can now!

Check this out... [cute] I'm going to speak with a french accent now..and between you and me

[whispers] I don't know how. [happy] ok.. here goes. [strong French accent] "Zat's life, my friend — you can't control everysing."

[giggles] isn't that insane? Watch, now I'll do a Russian accent -

[strong Russian accent] "Dee Goldeneye eez fully operational and rready for launch."

[sighs] Absolutely, insane! Isn't it..? [sarcastic] I also have some party tricks up my sleeve..

I mean i DID go to music school.

[singing quickly] "Happy birthday to you, happy birthday to you, happy BIRTHDAY dear ElevenLabs... Happy birthday to youuu."

Example by ElevenLabs · source ↗ · Runs in the Lab: this button opens the Audio studio. Pick the Eleven v3 model for audio tags.

Dialogue: several voices in one take

Label each line with a speaker and give each speaker a voice.

Speaker 1: [excitedly] Sam! Have you tried the new Eleven V3?

Speaker 2: [curiously] Just got it! The clarity is amazing. I can actually do whispers now—
[whispers] like this!

Speaker 1: [impressed] Ooh, fancy! Check this out—
[dramatically] I can do full Shakespeare now! "To be or not to be, that is the question!"

Speaker 2: [giggling] Nice! Though I'm more excited about the laugh upgrade. Listen to this—
[with genuine belly laugh] Ha ha ha!

Speaker 1: [delighted] That's so much better than our old "ha. ha. ha." robot chuckle!

Speaker 2: [amazed] Wow! V2 me could never. I'm actually excited to have conversations now instead of just... talking at people.

Speaker 1: [warmly] Same here! It's like we finally got our personality software fully installed.

Example by ElevenLabs · source ↗ · Assign a different voice to each speaker in ElevenLabs' dialogue mode.

Speaker 1: [starting to speak] So I was thinking we could—

Speaker 2: [jumping in] —test our new timing features?

Speaker 1: [surprised] Exactly! How did you—

Speaker 2: [overlapping] —know what you were thinking? Lucky guess!

Speaker 1: [pause] Sorry, go ahead.

Speaker 2: [cautiously] Okay, so if we both try to talk at the same time—

Speaker 1: [overlapping] —we'll probably crash the system!

Example by ElevenLabs · source ↗

Lesson 2: pauses, emphasis and pronunciation

"Ellipses (…) add pauses and weight. Capitalization increases emphasis."

It was a VERY long day [sigh] … nobody listens anymore.

Example by ElevenLabs · source ↗ · Ellipses add pauses and weight; CAPITALS add emphasis. Runs in the Lab: this button opens the Audio studio. Pick the Eleven v3 model for audio tags.

The term "/ˌbaɪoʊˈkemɪstri/" refers to the study of chemical processes.

Example by ElevenLabs · source ↗ · Runs in the Lab: this button opens the Audio studio. Pick the Eleven v3 model for audio tags.

"Hold on, let me think." <break time="1.5s" /> "Alright, I've got it."

Example by ElevenLabs · source ↗ · Break tags work up to 3 seconds on v2 models. Eleven v3 does not support them: use ellipses or dashes instead.

"You're leaving?" she asked, her voice trembling with sadness. "That's it!" he exclaimed triumphantly.

Example by ElevenLabs · source ↗ · The narrative words are spoken too, so trim them in editing if needed.

• Keep text normalisation on, and spell out risky items: "Dr." becomes "Doctor", "Ctrl + Z" becomes "control z".
• Phone numbers, prices, dates, addresses, links and units are the most common troublemakers.
• Speed runs from 0.7 to 1.2; pacing also comes from the voice's original recording.

Lesson 3: design a brand-new voice from words

Voice Design v3 creates a voice from a description, "fully compatible with Eleven v3 and supports audio tags". Describe age, accent, gender, timbre, pacing, quality and emotion; say the language; avoid effect words like reverb or phone.

Native <Language>. <Gender>, <Age range>. <Quality level>.
Persona: <2–5 words>. Emotion: <2–3 adjectives>.
<1–2 sentences about timbre, pacing, delivery>

Example by ElevenLabs · source ↗ · The official template: fill in the brackets.

Excellent audio quality. A man in his 30s to early 40s with a thick British accent speaking at a natural pace like he's talking to a friend.

Example by ElevenLabs · source ↗ · Guidance 40%.

An older woman with a thick Southern accent. She is sweet and sarcastic.

Example by ElevenLabs · source ↗ · Guidance 35%.

Dramatic voice, used to build anticipation in movie trailers, typically associated with action or thrillers

Example by ElevenLabs · source ↗ · Guidance 20%.

Native Arabic, soft Gulf (UAE) accent influence. Female, 30–40. Excellent quality. Persona: professional customer service agent. Emotion: warm, confident, polite. Velvety timbre with a calm tone, measured pacing, and gentle intonation, maintaining close-mic proximity for a high-fidelity, artifact-free signal. Clear presence and gentle emphasis on customer-friendly phrases to ensure easy understanding.

Example by ElevenLabs · source ↗ · Guidance 35%.

Lesson 4: clone your own voice

• Record "a clean recording with no background noise, room reverb, or multiple speakers, at a consistent volume and tone".
• Mic about 20 cm away, with a pop filter; peaks around -6 to -3 dB.
• Keep one performance style: do not mix animated and calm reading.
• Upload MP3 at 192 kbps or higher.

Lesson 5: sound effects that sound real

Up to 30 seconds per sound, with seamless looping and four variations each time. The model understands "natural language as well as audio terminology" like whoosh, impact, ambience, one-shot, loop, stem or braam.

Heavy wooden door creaking open

Example by ElevenLabs · source ↗ · Runs in the Lab: this button opens Sound Effects in the Audio studio.

Footsteps on gravel, then a metallic door opens

Example by ElevenLabs · source ↗ · Runs in the Lab.

high-quality, professionally recorded footsteps on grass, sound effects foley

Example by ElevenLabs · source ↗ · Runs in the Lab.

Old-school funky brass stabs from a vinyl sample, stem, 88 bpm in F# minor

Example by ElevenLabs · source ↗ · Runs in the Lab.

Lesson 6: write music prompts like a producer

ElevenLabs' music guide says every prompt should answer five questions: genre, mood, instrumentation, tempo and production era. Studio words like "sidechained", "tape saturation" or "plate reverb" change the result, and "start with", "then", "bring in" shape the arrangement.

Dreamy, psychedelic, slow Indie Rock, reverb-soaked vocals, retro keys, catchy chorus, analog, phased guitars, liminal, nostalgic feeling, anthem.

Example by ElevenLabs · source ↗ · Runs in the Lab: this button opens Music in the Audio studio.

An epic track for a cowboy show, wild west, cinematic sound design, guitar twanging with awesome orchestral elements crescendoing to a powerful finale, soundtrack.

Example by ElevenLabs · source ↗ · Runs in the Lab.

Extremely dark, tense and powerful, cinematic sound design, electronic hybrid, trailer music, evil, braam, braam horns, impacts, boom, rising tension, completely instrumental.

Example by ElevenLabs · source ↗ · Runs in the Lab.

synthwave arpeggio anthem, F minor, 128 BPM, neon nostalgia, analog polysynth pads

Example by ElevenLabs · source ↗ · Runs in the Lab.

More power tools

• Voice Changer (speech to speech): "Transform any source audio into a different, fully cloned voice without losing the performance nuances of the original." Up to 5 minutes per clip. Runs in the Lab as Speech to Speech.
• Dubbing into 90+ languages, keeping "the emotion, timing, tone and unique characteristics of each speaker".
• Scribe v2 speech-to-text in 90+ languages, with up to 32 speakers.
• Studio for audiobooks and podcasts, and Agents for live voice assistants.

Plans

• "The free plan does not include a commercial license and cannot be used for any commercial purpose"; free content must credit ElevenLabs.
• Unused credits roll over up to two months' worth; they are lost if you downgrade or cancel.

Run ElevenLabs in the Lab

AI Whisperer Lab connects to ElevenLabs directly. In the Audio studio you get Text to Speech with Eleven v3, Multilingual v2 and Flash v2.5, plus Voice Cloning, Speech to Speech, Sound Effects and Music, with no ElevenLabs subscription: you pay per run, see the price before you click, and your credits never expire. Your cloned voices stay private to your account.

FAQ

Sources: Models · TTS best practices · Voice Design · Sound Effects · Music best practices · Pricing · Use policy