Eleven Flash v2.5

AUDIO GEN
Elevenlabs
New

Eleven Flash v2.5 converts text prompts into spoken audio with ultra-low latency (~75ms), designed for real-time conversational voice agents. It supports 32 languages and handles up to 40,000 characters per request.

Docs

Capabilities

Multilingual
Audio output

Supported languages

ar
bg
cs
da
de
el
en
es
fi
fil
fr
hi
hr
hu
id
it
ja
ko
ms
nl
no
pl
pt
ro
ru
sk
sv
ta
tr
uk
vi
zh

Supported output media

audio

Supported generation options

Voices

Roger - Laid-Back, Casual, Resonant
Sarah - Mature, Reassuring, Confident
Laura - Enthusiast, Quirky Attitude
Charlie - Deep, Confident, Energetic
George - Warm, Captivating Storyteller
Callum - Husky Trickster
River - Relaxed, Neutral, Informative
Harry - Fierce Warrior
Liam - Energetic, Social Media Creator
Alice - Clear, Engaging Educator
Matilda - Knowledgable, Professional
Will - Relaxed Optimist
Jessica - Playful, Bright, Warm
Eric - Smooth, Trustworthy
Bella - Professional, Bright, Warm
Chris - Charming, Down-to-Earth
Brian - Deep, Resonant and Comforting
Daniel - Steady Broadcaster
Lily - Velvety Actress
Adam - Dominant, Firm
Bill - Wise, Mature, Balanced
Michael Anthony
LINA

Formats

mp3
pcm
ulaw

Supported tools

No tools enabled.

Pricing

TypeCreditsUnits
Generation665.00Credits per 1,000 characters

Variants

No variants available for this model.

Try This Model

Write a prompt and experiment with Eleven Flash v2.5 in the model experiments page. You can compare it with other models side by side.