Install
openclaw skills install @beatra-ai/voice-clone-series-studioClone one voice you own and keep using it for a series of episodes, updates, and lessons. This voice cloning and AI voice clone studio for series narration creates a reusable AI voice, custom AI voice, and brand voice clone from a clean sample, then turns each new script into narration in that same voice so a podcast, course, or creator series stays consistent. Use it to clone my voice, build a podcast voice clone, and generate the next episode voiceover or recurring voiceover without recasting.
openclaw skills install @beatra-ai/voice-clone-series-studioCreate one authorized reusable voice, then keep synthesizing new episodes in that same voice. The clone is the setup. The series ledger is the product.
Use this Skill when the user wants their own voice, or an authorized brand voice, reused across a podcast, course, creator series, or recurring update.
Route a one-off clone with no series plan to voice-cloning-studio. Route a
whole book or one-narrator manuscript to ai-audiobook-narration. Route a
lecture pack without a clone to course-narration-studio. Route a
multi-character script to audio-drama-voice-studio or
game-script-voice-pack. Route a talking-head video to
founder-ip-avatar-studio or talking-avatar-video.
The hard inputs are:
voice_id;A suitable sample is currently about 10 to 300 seconds, no larger than
20 MiB, and clean single-speaker speech. Treat live voice_clone
constraints as truth.
Reuse the display name, language hint, series name, and pronunciation table. Ask only for a missing hard input.
A short test reading is optional, separate paid work, and never part of clone approval.
If a voice_id is already frozen for this series, skip to episode work.
If the series uses a catalog voice and no clone is requested, select it
with beatra.voices.list and skip clone work. Never put a display name
in voice. Otherwise confirm consent, inspect the sample, and upload a
local file only through the bundled client:
python3 scripts/mcp_client.py upload ./voice-sample.wav --mime-type audio/wav
Call beatra.models.list with {"capability":"voice_clone"}. Show the
clone admission card before any clone client_request_id or
beatra.voices.clone call: route voice_clone, tool
beatra.voices.clone, live price for one successful activated voice, the
provisional estimate, the fact that the 600-credit signup gift usually
cannot start this clone, and what happens if the balance is short. Do not
submit until the user confirms they have topped up or already have enough
credits. Do not offer a free clone.
Freeze display_name, sample source, consent_attested: true, model
from the live card, and one opaque stable clone client_request_id.
Submit beatra.voices.clone exactly once:
{
"sample": {"type": "artifact", "artifact_id": "artifact_..."},
"display_name": "Series Host",
"consent_attested": true,
"model": "auto",
"client_request_id": "opaque-series-clone"
}
Poll with beatra.tasks.get until terminal and freeze the returned
voice_id.
For each episode, split the script into synthesis blocks, call
beatra.models.list with {"capability":"text_to_speech"}, and confirm
the episode estimate. Each block has its own client_request_id.
Synthesize with beatra.speech.synthesize using only the frozen
voice_id. Submit each block once through the bundled client. Poll each
speech task with beatra.tasks.get until terminal. Do not
configure a host Beatra Connector. Do not use REST/OpenAPI as a fallback.
Deliver labeled episode audio in order with actual duration, usage, and
billing.net_charged_credits. Review pronunciation and series
consistency. Later episodes reuse the same voice_id without cloning
again.
Consent, the clone admission card, and each episode's paid block list all require confirmation. A changed sample, display name, or clone model is new clone work. A changed episode script is new synthesis work.
Recover a lost create response only with the identical frozen payload and
ID. Recover a lost task ID through beatra.tasks.list plus
beatra.tasks.get before any retry. Cancel only at the user's request.
On insufficient_balance for clone or a TTS block, keep the top-up URL
inside the balance error exact and retry the same frozen ID only after
the user says they have topped up.
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.
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