ModelRefs / Voice AI — Canonical Workflow
Voice AI — Canonical Workflow
Canonical Voice AI workflow: ASR, LLM, TTS, latency budgets and deployment patterns.
Overview
Voice AI combines speech-to-text, an LLM and text-to-speech behind a low-latency turn-taking pipeline. The canonical stack budgets every hop for sub-second response so conversations feel natural over the phone or in real-time apps.
Implementation profile
| Category | audio-models |
|---|---|
| Implementation maturity | production |
| Evidence status | incomplete |
| Primary use cases | customer-support |
| Deployment options | managed-api, edge |
| Architectures | serverless-api, edge-runtime |
Candidate models with published references
Coverage means the model is a candidate worth evaluating for this workflow, not a ranking or a recommendation. Models whose reference pages are still in review are omitted.
Benchmarks relevant to this workflow
swe-bench, gpqa, mmlu, simpleqa, mgsm, mmlu-pro.
Relevance is a coverage signal from the canonical registry. Each benchmark only describes its own protocol and date, so confirm the harness matches your workload before treating a score as evidence.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Voice AI — Canonical Workflow.