OIP system: Voice
Voice
A generated article for one OIP shelf. It lists every operation in this API/CLI/MCP/device/model/core subsystem, links each leaf article, and gives the ledger path for proof.
This page is the operating article for one build subsystem. It is generated from live directory rows. If a task belongs to this subsystem, scan the operations below, open the matching capability article, run only the exact object named there, and verify by receipt.
Kind: model. Capabilities: 4. Machine system map: /api/dispatch?map=VOICE&format=markdown. Root: /a/oip.
Operations
VOICE_SAY
Make a spoken-audio FILE and return its public URL (does NOT send it). INVOKE: VOICE_SAY]<text>|<voice>[/VOICE_SAY] Use when: you need to voice say Arguments: $1 | $2. Human article: [/a/oip-capability-voice-say. Machine doc: ?key=VOICE_SAY&format=markdown. Invocation history: /api/invocations?object_id=VOICE_SAY.
VOICE_TRANSCRIBE
Transcribe inbound audio to TEXT (OpenAI whisper-1). INVOKE: VOICE_TRANSCRIBE]<public_audio_url>[/VOICE_TRANSCRIBE] Use when: you need to voice transcribe Arguments: $1. Human article: [/a/oip-capability-voice-transcribe. Machine doc: ?key=VOICE_TRANSCRIBE&format=markdown. Invocation history: /api/invocations?object_id=VOICE_TRANSCRIBE.
VOICE_SEND
Speak a reply INTO a chat (recommended audio-out). INVOKE: VOICE_SEND]<chat>|<words to speak>|<voice>[/VOICE_SEND] Use when: you need to voice send Arguments: $1 | $2 | $3. Human article: [/a/oip-capability-voice-send. Machine doc: ?key=VOICE_SEND&format=markdown. Invocation history: /api/invocations?object_id=VOICE_SEND.
VOICE
Invokable OIP capability. Human article: /a/oip-capability-voice. Machine doc: ?key=VOICE&format=markdown. Invocation history: /api/invocations?object_id=VOICE.