notes from ElevenLabs TTS experiment

Inizia individuando il percorso di rendering di ElevenLabs TTS e il codice che gestisce l’header della risposta, quindi traccia come sono attualmente rappresentati il lavoro durevole e la pulizia. Il lavoro è completo quando la history-item-id viene conservata prima di restituire l’audio, viene ritentata l’eliminazione ritardata, vengono controllati entrambi gli endpoint della cronologia, viene segnalato un errore terminale e vengono utilizzati scope di lettura e scrittura separati.

Alert text is user data. Design for minimizing what ElevenLabs ever holds; deletion is cleanup, not prevention.

enable_logging=false does not work. Measured: a ZRM request returned HTTP
200 and a history-item-id header — it wrote a history entry exactly like the
logging-on request, with no eligibility error. ZRM is gated to eligible
Enterprise accounts; on a normal key the parameter is accepted and silently does
not apply. Never treat a 200 as proof of non-retention.

Deleting the history item does work, but not immediately. Measured at +3 ms
after the audio response completed:

• DELETE /v1/history/{id} → 404 history_item_not_found
• GET /v1/history/{id}/audio → 200, audio present

The audio is live and fetchable on their servers before the history record is
addressable for deletion. A 404 on DELETE means "not there yet", not "nothing
stored" — never infer deletion from it.

Therefore: a delayed delete queue, not an inline delete.

• Persist the history-item-id (response header) durably at render time,
  before returning audio to the user. It is the only handle; a crash between
  render and delete orphans data nothing can later remove.
• Delete after a delay, with backoff retries on the not-found case.
• Alert on terminal failures. A failed delete is silent and leaves live audio.
• The delay is unmeasured — a 0/250/750/2000/5000 ms ladder was written but never
  confirmed against the live API. Measure it and set the first attempt past the
  window; don't assume.

Verification must handle inconsistent error shapes. DELETE-missing is 404,
but GET /v1/history/{id} on a missing item is 400 with
detail.status: invalid_id (not 404). Check both the history item and its
/audio endpoint — in one run the audio outlived the record.

Keys need their own scopes for cleanup: speech_history_write to delete,
speech_history_read to verify. A TTS-only key gets 401 missing_permissions
and the cleanup silently no-ops. Provision this before launch.

Even a verified delete is weaker than ZRM. ElevenLabs states debugging and
moderation logs may retain related data, and backups may persist up to 30 days.
User-facing copy must say "deleted from history" — never "never stored."