Skip to content
Back to skills

Broker Account Voice

ASecurity

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.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 29, 2026
ai-agentspythonbashapi

Works with

  • cli
  • api
  • mcp

Security analysis

A100/100

Pro scans all 13 files and shows the line behind each finding

Scanned September 29, 2026

npx -y skills add beatra-ai/beatra-skills --skill broker-account-voice --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Broker Account Voice?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Broker Account Voice
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/beatra-ai-broker-account-voice/badge)](https://www.skillsdirectory.com/skills/beatra-ai-broker-account-voice)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: "broker-account-voice"
description: "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."
---

# 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. Translate the prose; keep the URL. Do
   not retry until the desk says they have topped up.

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

```json
{"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. Translate the prose; keep the URL. Do
   not retry until the desk says they have topped up.

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.

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

```json
{"capability": "text_to_speech"}
```

```text
printf '%s' '{"input":"<the written line for this slot>","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.

## 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
  [Account opening voice workflow](references/workflow.md).
- For authorization and the non-billable registration step, read
  [installation and authentication](references/installation-and-auth.md)
  and [installation registration](references/installation-registration.md).
- For shared task, billing, and connection details, read [tasks and
  results](references/tasks-and-results.md), [billing, errors, and
  recovery](references/billing-errors-and-recovery.md), and [Bundled MCP
  Client diagnostics](references/mcp-connection.md).
- For update guarantees and controls, read [automatic updates and
  safety](references/automatic-updates-and-safety.md). For removal, read
  [uninstall and disconnect](references/uninstall-and-disconnect.md).

## 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](references/automatic-updates-and-safety.md).

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

Files in this skill

  • SKILL.md8 KB
  • manifest.json2.9 KB
  • references/automatic-updates-and-safety.md1.9 KB
  • references/billing-errors-and-recovery.md3.6 KB
  • references/installation-and-auth.md5.7 KB
  • references/installation-registration.md1 KB
  • references/mcp-connection.md1.2 KB
  • references/tasks-and-results.md2.2 KB
  • references/uninstall-and-disconnect.md2.7 KB
  • references/workflow.md2.3 KB
  • scripts/authorize.py21.8 KB
  • scripts/mcp_client.py60.1 KB
  • scripts/uninstall.py10.8 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…