ElevenLabs Flash v2.5
converts written text into spoken audio. ElevenLabs, Cartesia.fact-checked, all required fields present, publicly visiblereal-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
Pricing
- Billing model
- Per character
- Rate
- $0.05 per 1k characters
Last verified May 23, 2026
Benchmarks
Community Elo (blind votes)
TTS ArenaListed as: Eleven Flash v2.5
- Rank
- #10
- Elo
- 1531
- Win rate
- 55%
- Votes
- 3,289
Verified 2026-05-23
Speech Arena quality (AA)
Artificial Analysis TTSListed as: Flash v2.5
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 Flash v2 | $150.0000 | $60.0000 |
| Eleven Flash v2 | $150.0000 | $60.0000 |
| Eleven Flash v2.5 | $150.0000 | $60.0000 |
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