Memory

Account Opening Voice Pack

Try it

Turn written account-opening steps into one account opening voice clip per labeled cue. This account opening guidance studio records each teller guidance clip and KYC step voice from the steps the desk already wrote, then delivers 8 to 20 account opening audio files. Use it for brokerage onboarding audio that keeps one step on each clip.

What it does

Turn written account-opening steps into one account opening voice clip per labeled cue. This account opening guidance studio records each teller guidance clip and KYC step voice from the steps the desk already wrote, then delivers 8 to 20 account opening audio files. Use it for brokerage onboarding audio that keeps one step on each clip.

The skill document

Account Opening Voice Pack

Turn written account-opening steps into one spoken clip per labeled cue. Deliver 8 to 20 reads. Cover welcome, materials, and identity first.

Scope and adjacent routes

Use this Skill when a desk needs labeled account-opening guidance clips from steps it already wrote.

Route a phone-tree menu to ivr-voice-pack. Route generic narration to voiceover-narration-studio. Route shop booking notices to demo-booking-confirm.

Read only the supplied step list. Do not invent a step, a document, a yield figure, or an approval outcome.

Collect the opening steps

Hard inputs are:

  • the account-opening steps the desk already wrote;
  • a pronunciation table whenever names, product terms, or branch names appear;
  • how many clips the pack should contain, or permission to use the default of 10;
  • likeness and voice rights when a cloned teller voice will appear.

Reuse already-known language and a frozen voice_id. Ask only for a missing hard input. A count outside 8 to 20 is still doable: confirm that pack size and its live cost.

Do not invent a materials line, a yield, or a reading. File access is not consent.

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

Plan the free slot list

Write a labeled account-opening voice list before any paid clone or speech. Default ten slots unless the desk names another count in 8 to 20: welcome, materials, identity, bank-link, risk-grade, e-sign, password, deposit, app, and complete. Each slot records the spoken line from the written step list and whether it uses a catalog voice or a clone.

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

Safe defaults:

  • one beatra.speech.synthesize call per slot;
  • model: "auto" only when every live speech card supports the language;
  • format: "mp3"; speed: 1.0;
  • one brand voice for the whole pack.

Keep each submitted input at or below 50,000 characters. Split on sentence boundaries. Write short spoken sentences from the list.

Inspect an authorized clone sample when clone is requested. 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 or beatra.speech.synthesize.

Confirm clone, then speech

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

If the desk wants a cloned teller 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 (https://console.beatra.ai/wallet?intent=buy). Translate the prose; keep the URL. Do not retry until the desk says they have topped up. Do not recommend ¥198.

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 opening-step cue 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 (https://console.beatra.ai/wallet?intent=buy). Translate the prose; keep the URL. Do not retry until the desk says they have topped up. Do not recommend ¥198.

Submit each speech slot once through bundled scripts/mcp_client.py. Poll beatra.tasks.get. Read actual audio MIME, duration, and size, and billing.net_charged_credits. Do not promise the prepaid estimate is the final charge. A script preview is not the audio review.

Review, deliver, and recover

Review that every clip uses the same voice and that names match the pronunciation table and the written step list. Report only what the host can actually hear.

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 line, voice, or speed is a new card and a new ID. Cancel only when the desk 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"}
printf '%s' '{"input":"","voice":"voice_...","format":"mp3","client_request_id":"opaque-broker-speech-01"}' | python3 scripts/mcp_client.py call beatra.speech.synthesize

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

References by task

  • For slot lists, payloads, and recovery, read Account opening voice 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 or speech 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

Related skills

Turn a written customer-onboarding step list into one customer onboard voice clip per labeled cue. This onboarding-step voice studio records each customer onboarding audio and step list voice from the steps the enablement team already wrote, then delivers 8 to 20 customer onboard voice pack files. Use it for onboarding clip packs that keep one written step on each clip.

Turn a written visitor reception script into one visitor reception voice clip per labeled cue. This front desk voice studio records each reception script audio and visitor greeting voice from the script the desk already wrote, then delivers 8 to 20 visitor desk voice pack files. Use it for visitor reception voice packs that keep one cue on each clip.

Turn a written credit-card benefits table into one credit-rights voice clip per labeled cue. This benefits-table voice studio records each card-rights audio and rights-table voice from the list the desk already wrote, then delivers 8 to 20 credit-rights voice pack files. Use it for card-rights clip packs that keep one table item on each clip.

Turn confirmed booking facts into one booking confirmation voice clip per labeled notice. This appointment confirm audio studio writes speakable reschedule voice clips and cancel booking voice lines for a shop, then records 8 to 20 reservation confirm voice reads. Use it for shop booking voice packs that stay one line, one clip.

Turn a user-supplied product factsheet and authorized stills into one wealth product talking clip per still. This product factsheet talking video studio writes a speakable product highlights talking clip for each photo, then animates a 2 to 15s product factsheet talking clip. Use it for wealth product talking pack and factsheet talking video pack work that stays one photo, one clip.

Turn user-supplied account-opening material checklist lines into a four-to-eight still KYC guide set. This checklist-to-guide studio lays out each named material as its own still. Use it for account-opening material graphics, KYC guide stills, materials checklist cards, and a KYC materials pack.