Turn already-written short sleep stories into one spoken clip per labeled story. This sleep story voice studio records each short sleep-story voice from the pages the producer already wrote. Use it for sleep stories, bedtime story reads, bedtime narration, and short sleep-story voice packs.
Installs into .claude/skills of the current project.
Are you the author of Sleep Story Voice?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/beatra-ai-sleep-story-voice)
---
name: "sleep-story-voice"
description: "Turn already-written short sleep stories into one spoken clip per labeled story. This sleep story voice studio records each short sleep-story voice from the pages the producer already wrote. Use it for sleep stories, bedtime story reads, bedtime narration, and short sleep-story voice packs."
---
# Sleep Story Voice
Turn already-written short sleep stories into one spoken clip per
labeled story. Deliver 8 to 20 reads. Cover opening hush, first
scene, and landing first.
## Scope and adjacent routes
Use this Skill when a producer needs labeled short sleep-story
clips they can import into a player.
Route a long chapter serial to `ai-audiobook-narration`. Route a
radio ad break to `radio-drama-ad-break`. Route generic narration
to `voiceover-narration-studio`. Route sales voicemail to
`sales-voicemail-pack`.
Read only the supplied short stories. Do not add a plot, a
character name, a city, or a reading that is not on the list.
## Collect the short stories
Hard inputs are:
- the short sleep stories the producer already wrote;
- a pronunciation table whenever names or place words appear;
- how many clips the pack should contain, or permission to use the
default of 10;
- likeness and voice rights when a cloned 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 plot, a character name, a city, or a reading. File
access is not consent.
If names exist and the pronunciation table is empty, stop and collect
the readings.
A long serial is a different job. Keep this pack on short stories.
## Plan the free listen list
Write a labeled sleep-story list before any paid clone or speech.
Default ten slots unless the producer names another count in 8 to
20: opening hush, first scene, turning, landing, close, next-night,
rain bed, night walk, cabin, and river. Each slot records the spoken
text from the written short story and whether it uses a catalog
voice or a clone. Leave a missing story off the paid list.
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 producer 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 listen 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 producer 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 sleep story 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 listen 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 producer 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 sleep-story 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 story, voice, or speed is a new
card and a new ID. Cancel only when the producer 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 short story for this slot>","voice":"voice_...","format":"mp3","client_request_id":"opaque-sleep-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 listen lists, payloads, and recovery, read
[Sleep story 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
```