Design & media

Visitor Desk Voice Pack

Try it

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.

What it does

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.

The skill document

Visitor Desk Voice Pack

Turn a written visitor reception script into one spoken clip per labeled cue. Deliver 8 to 20 reads. Cover greeting, check-in, and escort first.

Scope and adjacent routes

Use this Skill when a front desk needs labeled visitor-reception clips from the reception script they already wrote.

Route generic narration to voiceover-narration-studio. Route a shift handoff checklist to shift-handoff-voice. Route civil-affairs material lists to civil-affairs-voice. Route elder checkup notices to elder-checkup-voice.

Read only the supplied visitor reception script. Do not invent a reception line, a visitor fact, or a policy not in the script.

Collect the reception script

Hard inputs are:

  • the visitor reception script the desk already wrote;
  • a pronunciation table whenever names, places, or coined words appear;
  • how many clips the pack should contain, or permission to use the default of 10;
  • likeness and voice rights when a cloned staff 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 reception line, a visitor fact, or a policy not in the script. 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 visitor-reception voice list before any paid clone or speech. Default ten slots unless the desk names another count in 8 to 20: greeting, check-in, badge, escort, waiting, contact, directions, safety, policy, and farewell. Each slot records the spoken line from the written reception script 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 script.

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 staff 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 visitor-reception 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 reception script. Report only what the host can actually hear. Do not invent a reception line, a visitor fact, or a policy not in the script.

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-visitor-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 Visitor desk 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 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 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 murder-mystery or indie-game script into a labeled multi-character voice pack. This AI game voice pack and character dialogue studio casts one consistent voice per role, records every line in script order, and delivers numbered clips with character IDs ready for an engine or tabletop production. Use it for game voice acting, indie game dialogue, murder mystery voiceover, multi character TTS, NPC voice acting, interactive story audio, tabletop voice pack work, and scripted game audio.

Build a labeled IVR voice pack for a phone tree: welcome, menu, hold, transfer, after-hours, and error prompts in one consistent brand voice. This phone tree voice studio and hotline voiceover shop records about twelve default prompts as a voice menu you can drop into the switch. Use it for IVR prompts, call center voice, auto attendant audio, and customer-service phone menus.

Turn a written hall window list into one hall guide voice clip per labeled cue. This window list voice studio records each hall window audio and window cue voice from the list the hall already wrote, then delivers 8 to 20 hall guide voice pack files. Use it for hall guide clip packs that keep one window on each clip.

Turn a written elder-checkup schedule into one elder checkup voice clip per labeled cue. This checkup schedule voice studio records each elder checkup notice audio and community checkup read from the schedule the office already wrote, then delivers 8 to 20 elder checkup voice pack files. Use it for elder checkup clip packs that keep one schedule item on each clip.