Eleven v4
ElevenLabs expressive, multilingual high-quality text-to-speech and dialogue synthesis model for narration, audiobooks and character performances.
Not published contextNot published max output
not-publishednot-published
PROVIDER INTELLIGENCE
ElevenLabs.
Verified model portfolio.
Specs, pricing availability and source-backed change history are normalized from the same canonical database used across SXF / AI.
4tracked models
0calculator-priced
2026-10-12last verified
MODEL PORTFOLIO
ElevenLabs models in the canonical DB.
Eleven v4 Turbo
ElevenLabs low-latency multilingual text-to-speech model for voice agents, interactive assistants and fast real-time synthesis.
Not published contextNot published max output
not-publishednot-published
ElevenLabs Scribe v2
ElevenLabs multilingual speech recognition for file transcripts, subtitle creation, speaker identification and keyterm-prompted transcription.
Not published contextNot published max output
$0.22 per 60 audio minutes (hourly API rate; add-ons extra)official-paid
ElevenLabs Scribe v2 Realtime
ElevenLabs low-latency streaming transcription via WebSocket, with partial/final utterances and voice-activity detection.
Not published contextNot published max output
$0.39 per 60 audio minutes (realtime WebSocket hourly API rate)official-paid
COMPARE ELEVENLABS