OPS:VOICE, Voice Operations

Load ops-rules before acting. Public repo (no personal data). Outbound: one draft → one approval → one send. If AskUserQuestion / Workflow are missing, follow Rule 10 in ops-rules (Hermes: numbered options / two-turn Telegram card; delegate_task).

Voice / phone / video interface. All API calls via curl, no SDK dependencies. Native macOS handlers (Phone.app, FaceTime, Zoom) require no credentials; programmatic channels (Twilio, Bland, ElevenLabs, Groq, Zoom schedule) resolve credentials via:

Credential resolution order: env vars → ops_cred_get (lib/credential-store.sh / keychain) → preferences.json → Doppler CLI (doppler secrets get <KEY> --plain) → password manager.

All sub-commands have a thin bash wrapper at bin/ops-voice, prefer it over inline curl when scripting.

Outbound comms guardrail (Rule 6): twilio-call, twilio-sms, and bland-call are 1:1 outbound channels and MUST follow the per-message approval gate, stage final draft, show full target+body, wait for explicit approval (AskUserQuestion or single-word chat approval), send one, then stage the next. Never batch.

---

Sub-commands

Parse $ARGUMENTS for the command keyword, then execute. Native handlers exit fast; API calls report status and (where relevant) a poll command.

---

phone <number>, Native Phone.app via Continuity

Routes through the linked iPhone. Requires macOS + iPhone signed in to the same iCloud account with Calls on Other Devices enabled. No credentials.

bin/ops-voice phone "+1234567890" --json
# {"ok":true,"channel":"phone","detail":"dialing +1234567890 via Phone.app (Continuity)"}

Under the hood: open "tel:<E.164>".

---

facetime <number-or-email> [--audio], FaceTime video/audio

Defaults to video. Pass --audio for FaceTime Audio (free, Apple↔Apple). Accepts phone numbers or Apple-ID emails.