ElevenLabs Multilingual v2
converts written text into spoken audio. ElevenLabs, Cartesia.fact-checked, all required fields present, publicly visiblenear-real-time
speech.dev has not published an operational assessment for this entry yet. Facts below are source-linked where available.
Overview
- Publisher
- ElevenLabs
- Lab
- elevenlabs
- Last updated
- 2026-05-23
- Modality
- converts written text into spoken audio. ElevenLabs, Cartesia.
a voice model trained on multiple languages. Quality varies enormously by language — "supports 40 languages" may be great in 3 and mediocre in the other 37.
en, es, fr, de, it, pt, pl, hi, ja, zh, ko, ar, tr, nl, sv, id, fi, uk, el, cs, ro, da, ta, ms
Pricing
- Billing model
- Per character
- Rate
- $0.10 per 1k characters
Last verified May 23, 2026
Benchmarks
Community Elo (blind votes)
TTS ArenaListed as: Eleven Multilingual v2
- Rank
- #11
- Elo
- 1528
- Win rate
- 57%
- Votes
- 3,360
Verified 2026-05-23
Speech Arena quality (AA)
Artificial Analysis TTSListed as: Multilingual v2
Indexed on Artificial Analysis text-to-speech comparison; quality Elo from Speech Arena.
Verified 2026-05-23
Technical
- Streaming
- Supported
- Hosting
- saas-vendor-cloud
- Self-hostable
- No
API access
WSSHTTPS streaming
API endpoints
wsshttps
SDK languages
python, typescript
Regions (vendor buckets)
Macro areas as published by the vendor (often broad; not a country list).
Compliance (vendor-published)
GDPR DPAHIPAA BAASOC 2 Type ISOC 2 Type II
LiveKit Inference
Listed on LiveKit Agents inference catalog · verified 2026-05-23
| Listed model | Build & Ship | Scale |
|---|---|---|
| Eleven Multilingual v2 | $300.0000 | $120.0000 |
LiveKit inference pricing (per million characters)
Suggest an update
Facts-layer corrections only — source URLs required. Opens a GitHub issue; a maintainer runs the content agent after triage. Not for operational notes.
Lab metadata: Update ElevenLabs · All request types · Full guide