Skip to main content
Models/ElevenLabs/Eleven v4

Eleven v4

ElevenLabs 🔊 Text-to-Speech

ElevenLabs' most expressive model (September 2026): tone, pacing and emotion read from the text, speaker identity held across long-form, audio tags, 85 languages, up to 10,000 characters per request.

Specifications

Input modalitiestext
Output modalitiesaudio
Streaming outputNo
Input price$385.00 / 1M

Pricing

$385.00 / 1M input characters

Platform credit pricing — live rates on the Models page.

Use Eleven v4 on Zubnet →

More from ElevenLabs

S
Scribe v2 Realtime
Ultra-low latency (<150ms) live speech recognition. 93.5% accuracy across 90+ languages. WebSocket streaming with VAD.
📝 Transcription
S
Scribe v1
Batch speech recognition with word-level timestamps and language detection across 99 languages.
📝 Transcription
S
Scribe v2 (Batch)
Batch state-of-the-art speech recognition: 98%+ accuracy, keyterm prompting, 90+ languages.
📝 Transcription
S
Scribe v2 Medical
Speech recognition fine-tuned for clinical audio: 35% fewer clinical errors than Scribe v2.
📝 Transcription