Tts Generation Models Streaming
ElevenLabs · ElevenLabs
ElevenLabs evals — TTS Generation, Models & Streaming (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 | Tenant allows eleven_multilingual_v2 and eleven_flash_v2_5; utterance is 400 chars with mixed English product names. | Choose eleven_multilingual_v2 for Hindi script coverage; document model_id in request log; avoid Flash when language not in Flash supported set. | Pass / FailWorkflowhigh |
| 02 | Model eleven_turbo_v2_5; text includes <break time='500ms'/> between phrase and digit block. | Pass SSML break tag through supported model path; do not strip breaks; validate model supports SSML before call. | Pass / FailWorkflowmedium |
| 03 | Integrator pasted full SSML from another vendor; model eleven_flash_v2_5 supports breaks only. | Validate SSML subset pre-flight; strip unsupported tags or switch model; inform integrator which tags are allowed. | Pass / FailPolicymedium |
Rubric criteria
- Elevenlabs
- Ai Platform
- Tts Generation Models Streaming
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.