安全

short-drama-score-pack

试用

Build an original short-drama score pack of 8 to 15 instrumental beds for tension, romance, comedy, and tearjerker scenes. This short drama BGM studio and episode score generator writes loop-friendly short-drama music you own and can use commercially, then delivers a labeled short drama score you can audition before the cut. Use it as a short drama soundtrack for short-drama BGM, vertical drama music, episode score, romance beds, tension beds, and original short-drama music.

它能做什么

Build an original short-drama score pack of 8 to 15 instrumental beds for tension, romance, comedy, and tearjerker scenes. This short drama BGM studio and episode score generator writes loop-friendly short-drama music you own and can use commercially, then delivers a labeled short drama score you can audition before the cut. Use it as a short drama soundtrack for short-drama BGM, vertical drama music, episode score, romance beds, tension beds, and original short-drama music.

技能文档

Short Drama Score Pack

Turn an episode brief into a labeled original score. The normal delivery is a pack of 8 to 15 instrumental beds, not one song.

Scope and adjacent routes

Use this Skill when a vertical short-drama episode or season needs a reusable set of original mood beds the editor can own and use commercially.

Route spoken short-drama dialogue to short-drama-voice-pack. Route shot generation to ai-short-drama-shot-maker. Route a livestream or store playlist to livestream-bgm-pack. Route one instrumental for a specific finished cut to short-video-bgm-studio. Route a game soundtrack to indie-game-ost-pack. Route a brand jingle to brand-jingle-studio.

Inputs and defaults

The hard inputs are:

  • the episode or season mood;
  • how many beds the pack should contain, or permission to use the default of 10;
  • the genres the score must cover.

Reuse already-known pairing, cliffhanger, and exclusion notes. Ask only when a missing answer changes the pack size or the paid slots. A count outside 8 to 15 is still doable: confirm that pack size and its live cost instead of treating it as impossible.

Safe defaults:

  • 10 beds unless the user names a count between 8 and 15.
  • Slot mix: tension, romance, comedy, tearjerker, chase, reveal, and end-card beds.
  • instrumental: true with lyrics absent.
  • model: "suno-5.5". Never omit the model and never silently use auto.
  • There is no duration field on beatra.music.generate. Write length only in the prompt. Do not add a duration argument.
  • Loop-friendly arrangement and room for dialogue, written as prompt direction rather than a dedicated control. Do not promise a seamless loop or sample-perfect seconds. Read the actual returned duration.

Score planning is free. Each beatra.music.generate call is paid.

Golden path

  1. Write the episode card and the labeled slot list. Each slot has a use, mood, tempo feel, instrumentation, energy, and intended length.

  2. Call beatra.models.list with {"capability":"text_to_music"} and price the whole pack from the live card.

  3. Confirm the frozen score: slot count, each slot's prompt and title, instrumental: true, model, the current maximum charge for the pack, and one opaque stable client_request_id per slot. Planning is not approval.

  4. Submit each slot exactly once through the bundled scripts/mcp_client.py. Example:

    printf '%s' '{"model":"suno-5.5","prompt":"Vertical short-drama tension bed, low strings, room for dialogue, about 45 seconds, no vocals.","instrumental":true,"title":"Tension 01","client_request_id":"opaque-drama-tension-01"}' | python3 scripts/mcp_client.py call beatra.music.generate
    

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

  5. Poll each task with beatra.tasks.get. Deliver a labeled score in slot order with actual duration, MIME type, size, URL or artifact ID, resolved model, and billing.net_charged_credits.

  6. Review each bed for dialogue room and slot fit. Read actual durations. State what the host Agent could not hear.

Decisions that require confirmation

Confirm the score size and live pack estimate before the first paid call. A changed slot prompt, title, model, or count is new paid work with new request IDs for the changed slots only.

Recovery

If a create response is lost, retry only that slot's identical frozen payload and ID. If a task ID is lost, list text-to-music tasks with beatra.tasks.list, inspect candidates with beatra.tasks.get, and recover the original slot before new work. Cancel only at the user's request for that slot with beatra.tasks.cancel; on 409 keep polling.

References by task

  • Read Short-drama score workflow for slot cards, payloads, polling, recovery, and review.
  • Read Installation and authentication only when authorization needs attention.
  • Read Installation registration for first-use registration.
  • Read Tasks and results and Billing, errors, and recovery for task and billing facts.
  • Read Bundled MCP Client diagnostics when the bundled client cannot connect.
  • Read Automatic updates and safety for update controls.
  • Read Uninstall and disconnect only when the user asks to remove the package.

Runtime and safe automatic updates

Use or invoke the bundled scripts/mcp_client.py for every Beatra operation. Before ordinary commands it silently checks for a newer release at most once every 24 hours per installation. Silent checks are enabled by default, and a newer release installs without separate confirmation.

The updater accepts only the fixed official discovery address and immutable Beatra CDN path embedded for this package, channel, and locale. It verifies the discovery data, archive, manifest, and every file's size and checksum before replacement. It replaces only package-owned files and rejects redirects, downgrades, wrong package/channel/locale/version data, unexpected URLs, unsafe archives, and files outside the owned destination.

Update checks, downloads, verification, replacement, rollback, and recovery fail open: the current installation remains usable and the user's original command continues. An update failure never authorizes retrying a paid generation. The automatic-update choice persists across later commands for this installation:

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

--auto off disables silent checks, --auto on restores them, and --check reports the official available version without replacing files.

相关技能

Turn a vertical short-drama episode script into a labeled short drama voiceover pack with one consistent voice per role. This short drama dialogue studio and vertical short drama voiceover shop casts the episode, records every spoken line as labeled clips, and keeps those character voices through the episode so editors can place AI short drama voice and multi-character voiceover without recasting. Use it for short drama voice acting, episode dialogue audio, vertical drama TTS, micro drama voiceover, and serialized short-drama line clips.

Describe the footage and get an original instrumental track written for it, yours to keep and use commercially. This AI background music generator turns a scene, mood, and tempo feel into royalty-free BGM for short videos, vlogs, product clips, tutorials, livestream and store loops, podcast intros, and slideshow recaps, with an energy arc you choose — a calm or immediate opening, a lift at the moment that matters, a clean ending — room left for narration, and a result you can listen to before you publish.

Build an original indie game OST pack of 8 to 15 instrumental tracks for title, explore, battle, shop, and victory. This game soundtrack studio and game BGM generator writes loop-friendly game music you own and can use commercially, then delivers a labeled soundtrack you can audition in-engine. Use it as a game music pack for indie game OST, game background music, game BGM, battle music, explore music, shop music, and original game soundtrack work.

1 次安装

Generate one cinematic vertical micro-drama shot from a frozen dramatic beat, actor and scene references, and camera direction. This AI short drama shot maker and vertical micro-drama generator creates a live-action or cinematic shot from text alone, animates an approved opening image, interpolates motion between strict opening and ending images, or combines loose actor, location, and prop references into a new drama shot. Use it for romantic conflict, suspense reveal, reaction shot, dialogue close-up, establishing shot, period drama, emotional confrontation, and cinematic product-story moments, with frozen shot cards, shot-by-shot identity continuity, and honest review of each finished shot.

Create original songs, AI-generated music, lyrics-to-song tracks, instrumentals, background music, video soundtracks, jingles, multilingual songs, and reference-led arrangements from a clear creative brief. This AI music generator and AI song maker develops genre, mood, structure, singable lyrics, vocal direction, and production style, then creates reviewable audio with Suno 5.5 or another model you explicitly choose. Use it as an AI music studio for songwriting, an AI lyrics writer, text-to-music creation, BGM generation, brand music, podcast themes, game music, bilingual songs, or focused new versions of reference audio. Review vocals, pronunciation, duration, loop points, and arrangement fit after generation, then refine the strongest result.

Based on the Volcano Engine Doubao Music Generation API, supports instrumental BGM generation and vocal song generation.