Fund Report Talking

---
name: "fund-report-talking"
description: "Turn a user-supplied fund quarterly report highlight sheet and authorized stills into one fund quarterly report talking clip per still. This fund quarterly report talking video studio writes a speakable report-fact talking clip for each photo, then animates a 2 to 15s quarterly highlight talking clip. Use it for fund quarterly report talking packs that stay one photo, one clip."
---

# Fund Quarterly Report Talking Clips

Turn a user-supplied fund quarterly report highlight sheet and authorized stills
into one talking clip per still. Deliver 2 to 8 clips. Do not stitch
them. Speak only report facts already printed in those highlights.

## Scope and adjacent routes

Use this Skill when a wealth advisor or fund marketer wants short
talking clips that explain quarterly report highlights they already
have.

Route a generic presenter that is not a quarterly report read to
`talking-avatar-video`. Route a product factsheet read to
`wealth-product-talking`. Route a dividend announcement read to
`fund-dividend-talking`. Route a user-supplied holding explanation to
`holding-review-talking`. Route fund page stills with no talking
video to `fund-page-set`. Route official earnings-script voice with no
video to `earnings-script-read`. Route silent product motion to
`product-video-studio`.

## Collect the highlight sheet

Hard inputs are:

- at least one accessible still the host Agent can inspect — a
  presenter portrait or a report graphic that will be the first
  frame;
- the fund quarterly report highlight sheet the advisor supplied
  (fund name, reporting period, portfolio or sector facts, manager
  commentary, and any printed metrics already on that sheet);
- a pronunciation table whenever fund names, tickers, 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, fund 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 a return forecast, market direction call, buy or sell
recommendation, or metric that is not on the highlight sheet. File
access is not consent.

If fund 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 quarterly report talking list before any paid clone,
speech, or video. Default three slots unless the advisor names another
count in 2 to 8: reporting period, printed portfolio or sector facts,
and manager commentary already on the sheet. Each slot records the
still, the spoken line from the supplied highlight sheet, 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`:

```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 highlight 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`:

```json
{"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 quarterly report 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 highlight 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.

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

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

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

```json
{"capability": "image_to_video"}
```

```text
printf '%s' '{"input":"The reporting period is the one already printed on this quarterly highlight sheet.","voice":"voice-ready-01","format":"mp3","speed":1.0,"model":"auto","client_request_id":"opaque-report-speech-01"}' | python3 scripts/mcp_client.py call beatra.speech.synthesize
```

```text
printf '%s' '{"image":{"type":"artifact","artifact_id":"art-report-01"},"driving_audio":{"type":"artifact","artifact_id":"art-speech-01"},"prompt":"A restrained quarterly report read with steady eye line and a stable camera.","duration":8,"client_request_id":"opaque-report-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
  [Quarterly report talking 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 version. 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](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
```