Skip to main content
POST
Trigger a voice-eval run

Authorizations

Authorization
string
header
required

Dashboard JWT token from Clerk

Headers

Idempotency-Key
string

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.

Required string length: 1 - 255
X-Test-Mode
enum<string>

Sandbox 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.

Available options:
true,
false

Body

application/json
golden_set_id
string
required

Golden set to execute.

Maximum string length: 200
agent_id
string

Voice agent under test (omit for provider-only A/B runs).

Maximum string length: 200
agent_version_id
string

Specific agent prompt version to evaluate.

Maximum string length: 200
trigger_source
enum<string>
default:manual

Trigger origin (defaults to manual).

Available options:
manual,
pre-deploy-ci,
scheduled
stt_provider
string

STT provider override (A/B testing).

Maximum string length: 100
tts_provider
string

TTS provider override (A/B testing).

Maximum string length: 100
llm_model
string

LLM model override (A/B testing).

Maximum string length: 200

Response

Run created — totals, latency, and simulation flags.

Run created — totals, latency, and simulation flags.

data
object
meta
object