elevenlabsReleased Feb 2, 2026

ElevenLabs: Eleven v3

Eleven v3 is a text-to-speech model from ElevenLabs. It produces emotionally rich, highly expressive speech with inline audio tags, supports 70+ languages, and has a 5,000-character request limit.

Provider endpoints1
Benchmark results1
Measured performance

Benchmark results

All leaderboards ↗
AA Provider Voice TTS Arena ↗Unversioned · provider native voices
1,177.6

Provider native voices · all categories · US + UK accents · 8 listed voices

95% CI 1,166.6–1,188.6 · n=4,904

Independent result
Access & cost

Prices across providers

1 quote
Rate
$0.10
USD / 1K characters
Price source ↗Checked Oct 17, 2026
Endpoint IDfal-ai/elevenlabs/tts/eleven-v3

Model specifications

Developer
elevenlabs
Modality
Audio
Context
Not reported
Maximum output
Not reported
Weights
Not reported
Released
Feb 2, 2026
Provider listed
Aug 20, 2025
First discovered
Oct 16, 2026

Exact identities

  • openrouterelevenlabs/eleven-v3
  • falfal-ai/elevenlabs/tts/eleven-v3
  • aa-tts49285d46-f230-416c-aa92-6322c9f60629

Sources

Updated Oct 18, 2026

More from elevenlabs

View all ↗
elevenlabsListed 10 days ago

ElevenLabs: Eleven Turbo v2

Eleven Turbo v2 is an English-only, low-latency text-to-speech model from ElevenLabs. It is suited for developer use cases where speed matters and only English is needed, and has a 30,000-character...

No reported score
No reported score
Price not listed
elevenlabsListed 10 days ago

ElevenLabs: Eleven Flash v2

Eleven Flash v2 is an English-only, ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time English use cases, and has a 30,000-character request limit.

No reported score
No reported score
Price not listed