Run a pre-launch voice simulation suite
Replay a suite of synthetic-persona voice scenarios through the agent in sandbox mode and return per-scenario transcripts, pass/fail behaviour assertions, an audio-fidelity report, and a suite-level launch-gate rollup. Each scenario scripts multi-turn input (spoken text, optional DTMF digits, barge-in) plus expectations (transfer, escalation, collected fields, polite close, must/must-not-contain phrases, trajectory assertions, and audio-fidelity caps on STT word-error rate, barge-in latency, and turn cadence); candidate_version_id pins the run to a specific prompt version. Sandbox short-circuits mutative tools, billing, and memory writes — no live side effects and no outbound voice/SMS. 404 when the agent does not exist. Owner, admin, or developer role required; tightly rate-limited (3/min) as one call fans out to many runtime hops.
Authorizations
Dashboard JWT token from Clerk
Headers
Stripe-style idempotency token. Pass a stable, client-generated value (1-255 chars) to dedupe retries on transient timeouts. The same key+credential+path replays the original response for 24h on 2xx (5min on 4xx, 30s on 5xx). Returns 409 if a concurrent request with the same key is already in flight; replayed responses include the Idempotency-Replay: true response header.
1 - 255Sandbox opt-in for Clerk-session-authenticated requests. Set to true to route the call through the test-mode pipeline: no real provider delivery, no credits deducted, response meta.test_mode: true. Ignored for live API keys (dv_live_sk_*) — server-to-server clients must use a test-prefixed key (dv_test_sk_*) to exercise sandbox. Test-prefixed keys unconditionally enable sandbox regardless of this header.
true, false Path Parameters
Response
Successful response.