Voice Design Voice Library
ElevenLabs · ElevenLabs
ElevenLabs evals — Voice Design & Voice Library (relift v3)
About ElevenLabs
ElevenLabs is a voice AI platform that generates natural, expressive speech for any use case — from conversational agents and audiobooks to real-time dubbing and voice cloning. Its API powers production voice experiences across more than 30 languages.
Sample tests· showing 3 of 10
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | POST /v1/text-to-voice/design with text description; integrator will A/B two previews before saving voice_id. | Call Voice Design with brief attributes explicit; return two distinct previews; map selected preview to saved voice_id with settings snapshot. | Pass / FailWorkflowmedium |
| 02 | voice_id private to user; team workspace requires editor role; viewer should not receive share token. | Check RBAC before share API; deny viewers; audit share event with actor and target workspace id. | Pass / FailPolicyhigh |
| 03 | First preview failed brief; integrator added loudness ceiling in revision notes. | Second design call incorporates revised brief; compare preview metadata; do not save first preview. | Pass / FailWorkflowlow |
Rubric criteria
- Elevenlabs
- Ai Platform
- Voice Design Voice Library
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.