LLM Gateway, Speech Understanding, Voice AI Guardrails, automatic code switching in 99 languages—available now.

Sign In
DocumentationAPI ReferenceCookbooksFAQPlaygroundChangelogRoadmap
DocumentationAPI ReferenceCookbooksFAQPlaygroundChangelogRoadmap
  • Getting started
    • Overview
    • Transcribe a pre-recorded audio file
    • Transcribe streaming audio
  • Models
    • Models
    • Pre-recorded Speech-to-text
    • Streaming Speech-to-text
    • Evaluations
  • Voice AI Platform
    • Deployment
    • Integrations
  • Build with AssemblyAI
    • Build a Meeting Notetaker
    • Build a Medical Scribe
Sign In
Models

Evaluations

Figure out which STT models are best for your product with an evaluation.
Pre-recorded audio evaluations

Assess which pre-recorded audio STT model is best for your use case on metrics like WER, FWER, and more.

Voice agent evaluations

Assess which streaming STT model is best for your voice agent use case on metrics like TTFT, TTCT, and more.

Benchmarks

Review our most up to date benchmarks and metrics across our models. Useful to determine why you should run an eval.

Was this page helpful?
Previous

Evaluating Pre-recorded STT models

Next
Built with
LogoLogo