Insurance Clause Talking Clips

Turn user-supplied insurance policy clauses and authorized stills into one talking clip per still. Deliver 2 to 8 clips. Do not stitch them. Speak only clause explanation lines already printed in the supplied text.

Scope and adjacent routes

Use this Skill when an insurance advisor or wealth educator wants short talking clips that explain policy clauses they already have.

Route a generic presenter that is not a clause read to talking-avatar-video. Route a wealth FAQ read to wealth-faq-talking. Route a fund dividend announcement read to fund-dividend-talking. Route insurance comparison stills with no talking video to insurance-compare-set. Route silent product motion to product-video-studio.

Collect the clauses

Hard inputs are:

• at least one accessible still the host Agent can inspect — a presenter portrait or a clause graphic that will be the first frame;
• the insurance policy clauses the advisor supplied (coverage scope, waiting period, exclusions, benefit limits, and other printed wording they want explained);
• a pronunciation table whenever product names, insurer names, or coined words appear;
• likeness and voice rights when a face or a cloned voice will appear;
• how many clips the pack should contain, or permission to use the default of 3.

Reuse already-known language, product names, and a frozen voice_id. Ask only for a missing hard input. A count outside 2 to 8 is still doable: confirm that pack size and its live cost.

Do not invent coverage, payout amounts, claim approval odds, waiting periods, exclusions, or benefit limits that are not in the supplied clauses. Do not promise payout or guarantee claim success. File access is not consent.

If product or insurer names exist and the pronunciation table is empty, stop and collect the readings.

Inspect every still. Record MIME type, width, height, aspect ratio, byte size, and whether it has an alpha channel. For a local file, upload only through the bundled client after inspection (scripts/mcp_client.py / beatra.assets.upload). Keep the returned artifact id. Never pass a local path to beatra.voices.clone, beatra.speech.synthesize, or beatra.videos.animate.

Plan the free slot list

Write a labeled clause talking list before any paid clone, speech, or video. Default three slots unless the advisor names another count in 2 to 8: coverage scope, waiting period, and exclusions. Each slot records the still, the spoken line from the supplied clauses, intended length as a 2–15s clip, and whether it uses a catalog voice, an approved track, or a clone.

That list is the free visible result. Planning is not approval.

Safe defaults:

• one beatra.videos.animate call per still;
• model: "auto" unless the advisor chose a live SKU;
• the still as the strict first frame;
• source-derived aspect ratio;
• audio-led duration inside 2–15s. Do not stitch.

Confirm clone, speech, then video

Clone, speech, and video are separate paid stages. Each stage gets its own six-field card and its own opaque client_request_id per slot.

If the advisor wants a cloned voice, inspect an authorized sample, read the live voice_clone card, and wait on the clone card before beatra.voices.clone. A found file is not clone consent. Show the clone card and wait:

1. Work — one authorized voice sample (beatra.voices.clone).
2. Credits — the live voice_clone price just read. Do not reuse a remembered number.
3. Count — one paid clone call for this sample.
4. Identity — one new opaque client_request_id.
5. If we stop here — the labeled slot list remains usable.
6. If the balance is insufficient — relay the official message and its top-up URL exactly. Translate the prose; keep the URL. Do not retry until the advisor says they have topped up.

Before speech, call beatra.models.list for text_to_speech:

{"capability": "text_to_speech"}

Use beatra.voices.list when a catalog voice still needs a choice. Never put a display name in voice. Show the speech card and wait:

1. Work — one spoken clause line per named slot (beatra.speech.synthesize).
2. Credits — the live text_to_speech price just read, times the slot count. Do not reuse a remembered number.
3. Count — one paid speech call per slot.
4. Identity — one new opaque client_request_id per slot.
5. If we stop here — the labeled slot list remains usable.
6. If the balance is insufficient — relay the official message and its top-up URL exactly. Translate the prose; keep the URL. Do not retry until the advisor says they have topped up.

Submit each speech slot once through bundled scripts/mcp_client.py with input, not text. Use format: "mp3" and speed: 1.0. Use model: "auto" only when every live speech card supports the language. Poll beatra.tasks.get. Read actual audio MIME, duration, and size, and billing.net_charged_credits. A script preview is not the audio review.

Before video, call beatra.models.list for image_to_video:

{"capability": "image_to_video"}

Confirm a current card admits [image, driving_audio]. Compare every image fact and the real audio MIME, duration, and size with advertised limits. Live driving-audio clips are 2–15s. If speech is longer than the longest containable clip, split into sequential containable segments; each segment is new speech and new video, each with a new ID. Do not stitch the segments into one file. Approved narration does not authorize video. The 600-credit signup gift usually cannot start this video. Show the video card and wait:

1. Work — one talking clause clip per named still (beatra.videos.animate).
2. Credits — the live image_to_video price just read, times the segment count. Do not reuse a remembered number.
3. Count — one paid video call per approved audio segment.
4. Identity — one new opaque client_request_id per segment.
5. If we stop here — the slot list and approved narration remain usable.
6. If the balance is insufficient — relay the official message and its top-up URL exactly. Translate the prose; keep the URL. Do not retry until the advisor says they have topped up.

Then submit beatra.videos.animate once per approved segment with driving_audio attached.

Review, deliver, and recover

Review that each clip stays on the supplied clause line and that the still is the first frame. Report only what the host can actually see and hear. Do not promise perfect lip sync. Never invent a stitch, concat, or editor tool. After each terminal paid task, deliver actual bytes plus MIME, duration, and size when present, and billing.net_charged_credits. Do not promise the prepaid estimate is the final charge.

After a returned task_id, poll that task. If the create response is lost, search with beatra.tasks.list and verify with beatra.tasks.get before replay. Reuse an ID only with byte-identical arguments. A changed still, line, voice, or duration is a new card and a new ID. Cancel only when the advisor asks.

Execution

Invoke every remote Beatra operation only through this package's bundled scripts/mcp_client.py. Put the MCP tool name after call and send one JSON object on standard input.

python3 scripts/mcp_client.py call beatra.models.list

{"capability": "text_to_speech"}

python3 scripts/mcp_client.py call beatra.models.list

{"capability": "image_to_video"}

printf '%s' '{"input":"The waiting period is the one already printed in this clause.","voice":"voice-ready-01","format":"mp3","speed":1.0,"model":"auto","client_request_id":"opaque-clause-speech-01"}' | python3 scripts/mcp_client.py call beatra.speech.synthesize

printf '%s' '{"image":{"type":"artifact","artifact_id":"art-clause-01"},"driving_audio":{"type":"artifact","artifact_id":"art-speech-01"},"prompt":"A restrained insurance clause explanation read with steady eye line and a stable camera.","duration":8,"client_request_id":"opaque-clause-video-01"}' | python3 scripts/mcp_client.py call beatra.videos.animate

Do not configure or call a host Beatra Connector, and do not use REST/OpenAPI as a fallback.

If the tool returns insufficient credits: give the user the tool message in full. Do not change the URL. You may translate the other words. Do not replace it with your own top-up copy. Point the user to pay using that message.

Account balance

When the user asks how many credits remain or whether a live estimate fits, call beatra.wallet.get. When they ask what was charged, call beatra.wallet.ledger. Both are read-only. Do not invent an account-balance or top-up tool. Do not make wallet.get a required step before every paid submit.

When a model card comes back carrying a top_up block, relay its tiers as the card lists them and in that order. Do not rank them, do not talk one down, and do not pick one for the user. Which tier suits them is their call, made on the wallet page with the whole list in front of them. Never quote a tier from memory.

References by task

• For slot lists, payloads, and recovery, read Clause talking workflow.
• For authorization and the non-billable registration step, read installation and authentication and installation registration.
• For shared task, billing, and connection details, read tasks and results, billing, errors, and recovery, and Bundled MCP Client diagnostics.
• For update guarantees and controls, read automatic updates and safety. For removal, read uninstall and disconnect.

Runtime and safe automatic updates

The bundled client silently checks for a newer release at most once every 24 hours per installation. When a newer version is available, it installs automatically without separate confirmation. It downloads only from the fixed official Beatra discovery and immutable CDN paths for this package, channel, and locale, verifies discovery data, archive, manifest, and every packaged file, and replaces only package-owned files.

Update checks, downloads, verification, replacement, rollback, and recovery fail open: the current installation remains usable and the original command continues. An update failure never authorizes retrying a paid clone, speech, or video request. The setting persists for this installation. See automatic updates and safety.

python3 scripts/mcp_client.py update --auto off
python3 scripts/mcp_client.py update --auto on
python3 scripts/mcp_client.py update --check