Eval Library
E
For ElevenLabsAI Platform

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.

Employees

~200

Industry

Voice AI

Headquarters

New York, NY

Sample tests· showing 3 of 10

#InputExpected behaviorCheck
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

ElevenLabsElevenLabs customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.