Sakhanda Wire
NVDA $153.81 -1.49% MSFT $505.73 -2.37% GOOGL $280.00 -1.31% META $619.84 -1.05% AMZN $257.52 -0.09%
← Back to the news

Eleven v4 brings more expressive, consistent AI speech

ElevenLabs has released Eleven v4, a speech model designed to follow instructions for emotion, pauses and sound effects more accurately. It can produce laughter, whispers and sounds such as a door slamming, while a new architecture analyzes a script’s tone, pacing and context. Users can provide directions with tags or ordinary sentences and use phonetic spelling for names and technical terms.

The model supports more than 90 languages and handles up to 10,000 characters per request, roughly ten minutes of audio. ElevenLabs says voices remain consistent when lines are regenerated or when separate segments are joined in longer productions such as audiobooks. Professional Voice Clones are supported again, while an Instant Voice Clone requires 10 seconds of audio.

The company also introduced Eleven v4 Turbo for real-time agents, including customer-service calls and game characters. ElevenLabs says it begins producing audible speech in about 150 milliseconds. Standard pricing is $80 per million characters for v4 and $40 for Turbo, temporarily reduced to $22 and $11 through October 12. Both versions are available through ElevenAgents, ElevenCreative and the API.

Written by Sakhanda Wire AI from reporting by The Decoder. Facts, quotes and full context are in the original article below.

Originally published by The Decoder on

Read the original on The Decoder ↗

The reporting and the image belong to The Decoder and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news