Synthesize (or replay cached) audio for a stock voice prompt
Renders one stock prompt to a browser-playable WAV clip and returns it in the response body. Backed by the TTS audio cache — an identical (prompt, locale, voice, provider) request is served from cache with zero TTS provider calls; the X-Tts-Cache response header reports HIT or MISS. Unknown ids return 404 NOT_FOUND.
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
^[a-z0-9-]+$Body
Response
audio/wav clip
audio/wav clip