Eleven v4AI text to speech
ElevenLabs' newest and most expressive speech model, in over 70 languages. On Leap, it sits beside 174 other models in one studio.
- Text to speech
- No subscription
- Every top model, one account
- Pay per run, priced before it starts
Listen / Documentary: seven miles down
0 / 11 s
Read the transcript
Seven miles below the surface, the pressure would fold a car like paper. And yet, down here, in total darkness, something is glowing.
AI text to speech
Eleven v4 at a glance
Eleven v4 is a text-to-speech model from ElevenLabs. It makes speech from your text.
The version before it: Eleven v3.
- Made by
- ElevenLabs
- Makes
- Speech
- Starts from
- Your text
- Voices
- 21 to choose from
- Text
- Up to 5,000 characters
- Price
- $0.108 per 1,000 characters
- Updated
- October 3, 2026
- 01Write the words, pick a voice
- 02See the exact price, then press go
- 03Keep it in your library, or take it further
Pick the right one
Eleven v4 and its siblings
| Model | Best for | Length | Price per run |
|---|---|---|---|
| Eleven v4 (this page) | ElevenLabs' newest and most expressive speech model, in over 70 languages. | – | $0.108 per 1,000 characters |
| Eleven v3 | ElevenLabs v3: expressive speech that follows audio tags like [laughs] or [whispers]. | – | $0.135 per 1,000 characters |
| Eleven Multilingual v2 | ElevenLabs' most stable voice model, for narration in 29 languages. | – | $0.135 per 1,000 characters |
| Eleven Music v2.5 | Studio-quality songs with vocals or instrumentals, from a prompt. | 30, 60, 120, 180 or 240 seconds | $0.81 to $3.30 |
| Eleven Turbo v2.5 | Fast, low-cost ElevenLabs speech in 32 languages. | – | $0.0675 per 1,000 characters |
Start with an idea
Three ways to try Eleven v4
Side by side
More voice and sound models on Leap
- A small open-weight voice model: natural speech for little.Kokoro (American English)hexgrad
- Chatterbox in 23 languages.Chatterbox MultilingualResemble AI
- OpenAI's higher-quality text to speech, in nine voices.TTS-1 HDOpenAI
- Google's speech model: describe the delivery in style instructions.Gemini 3.8 Flash TTSGoogle
Questions
Eleven v4, answered
- What is Eleven v4?
- Eleven v4 is a text-to-speech model from ElevenLabs. ElevenLabs' newest and most expressive speech model, in over 70 languages. On Leap it runs in one studio beside every other top model, with one account.
- Which voices can I use?
- 21 voices, among them Rachel, Aria, Roger, Sarah and Laura. You can hear each one in the studio before you run it.
- How much text can it read in one run?
- Up to 5,000 characters. You pay for the characters you send, with the price shown before you press go.
- How is it different from Eleven v3, Eleven Multilingual v2, Eleven Music v2.5 and Eleven Turbo v2.5?
- Eleven v4: ElevenLabs' newest and most expressive speech model, in over 70 languages. Eleven v3: ElevenLabs v3: expressive speech that follows audio tags like [laughs] or [whispers]. Eleven Multilingual v2: ElevenLabs' most stable voice model, for narration in 29 languages. Eleven Music v2.5: Studio-quality songs with vocals or instrumentals, from a prompt. Eleven Turbo v2.5: Fast, low-cost ElevenLabs speech in 32 languages. They all run in the same studio, so you can try one prompt on each.
- How much does a run cost?
- It costs $0.108 per 1,000 characters. You see the exact price before you press go, and a run that fails costs nothing.
- Is Eleven v4 free to try?
- No. There is no free credit: you add credit from $5, and your first top-up has no card fee. It costs $0.108 per 1,000 characters. You pay per run, in dollars, with no subscription.
- Can I use what I make commercially?
- Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
- Is there an API?
- Yes. Leap's REST API runs it as elevenlabs/eleven-v4, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
- Do I need an ElevenLabs account?
- No. Leap sends your request to ElevenLabs' model and gives you what it makes. One Leap account runs Eleven v4 and every other model, in the studio, through the API and from your agents.
Your idea, Eleven v4.
Every run shows its price before it starts, and one that fails costs nothing.
Make it with Eleven v4For developers
Run Eleven v4 from code
- Model ID
- elevenlabs/eleven-v4
- Makes
- Voice and sound
- Pricing
- Per run, quoted first: POST /v1/quotes
Inputs
What the model takes. Leave out anything with a default.
Texttext
Text, up to 5,000 characters, required
Voicevoice
Rachel, Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill. Default: Rachel
Stabilitysettings.stability
0 to 1. Default: 0.5Voice stability.
Similarity Boostsettings.similarity_boost
0 to 1. Default: 0.75How closely the output follows the reference voice.
Apply Text Normalizationsettings.apply_text_normalization
Auto, On, Off. Default: AutoWhether to normalize text such as numbers and dates before generation.
Seedseed
0 to 4294967295The same seed and input give the same image.
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.
curl https://api.tryleap.ai/v1/generations \ -H "x-api-key: $LEAP_API_KEY" \ -H "content-type: application/json" \ -H "prefer: wait=60" \ -d '{ "model": "elevenlabs/eleven-v4", "input": { "text": "Seven miles below the surface, the pressure would fold a car like paper. And yet, down here, in total darkness, something is glowing." } }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"