beatra-ai/beatra-skills/beatra-ai-voice-studio

Claude Code and agent skill by beatra-ai/beatra-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use Beatra AI Voice Studio as an AI voice generator, text-to-speech workspace, and AI voiceover generator. Choose from the current voice library, turn scripts into ready-to-edit AI narration and voiceover, or create and reuse a custom brand voice through voice cloning. It supports short-video voiceover, script-to-voiceover, course narration, ordered audiobook narration, supplied multilingual text to speech, Cantonese text to speech, and recurring brand audio, with current price estimates, clear output planning, and delivery organized by chapter, language, and use case.

Install

npx vskill@latest install beatra-ai/beatra-skills/beatra-ai-voice-studio

SKILL.md

The same SKILL.md was published earlier as beatra-ai/beatra-skills/beatra-ai-voice-studio.

Beatra AI Voice Studio

Choose the smallest voice or audio workflow that delivers the user's goal: single voiceover, Smart Voice Director pacing, multi-speaker dialogue, speech-to-speech conversion, ordered long-form or multilingual tracks, three-route voice cloning and slot lifecycle, speech transcription, sound effects, stem separation, voice isolation, or broadcast loudness normalization. Keep this flagship Studio as the coordinating hub across mixed audio workflows.

Scope and routes

At the unified entrance, split focused requests to narrower specialized Skills when appropriate, or coordinate full audio pipelines directly here:

User outcomeBest route
One standalone short-video, ad, or promo readshort-form-voiceover-audio
An audiobook or one-narrator chaptered manuscriptai-audiobook-narration
A single-host podcast episode or recurring showai-podcast-voiceover
Multilingual dubbing with target-language scripts suppliedai-multilingual-dubbing
Focused one-off cloning without mixing other audio tasksvoice-cloning-studio
Multi-speaker dialogue, speech-to-speech, transcription, sound effects, stem separation, voice isolation, loudness normalization, or mixed audio productionContinue here and maintain one production ledger

Verify active tools via scripts/mcp_client.py tools. This flagship Studio does not render video frames, lip-sync faces, or publish to external feeds; route video/avatar finishes separately while keeping all voice and audio work here.

Read intent and routing and the shared speech and audio guide before mixing multiple audio tools.

Inputs and defaults

Require these hard inputs before billable execution:

  • Synthesis / dialogue / direction: final approved text or multi-turn lines

(or permission to draft/direct speakable copy and show it first), an exact current voice_id looked up fresh with beatra.voices.list, and language ONLY when the user supplies one—never interrupt simply to ask for a language.

  • Voice cloning: clean single-speaker sample, display_name, and explicit

confirmation that it is the user's own voice or explicitly authorized by the speaker—confirmed before any local sample upload.

  • Audio tools (`convert`, `transcribe`, `process`): valid uploaded artifact

or public HTTPS source URL, exact consent where voice identity matters, and target operation parameters (prompt for generate_sfx).

Use restrained defaults unless the user asks otherwise: model: "auto", format: "mp3", speed: 1.0, volume: 1.0, pitch: 0, no emotion, and no sample_rate. Keep the user's characters and wording as written: never convert simplified and traditional characters or swap dialect words unless the user asks, and never call a changed text unchanged. Never manually strip / pause tags or invent custom bracketed vocal-effect cues—use Smart Voice Director (prepare_script) for expressive pacing and delivery direction.

Before the connection is ready

When Allow is still pending at the end of a turn, finish and deliver everything that needs no connection, in the format the user asked for: the prepared reading script, voice-selection criteria (gender, timbre, language), and the control defaults. Name a voice only after beatra.voices.list returns. Say in one line that Allow is the one-time sign-in that connects their Beatra account, not a second confirmation of this request, and that the audio runs on their next message after it. Do not fill the gap with another tool or service.

Golden path

  1. Identify the minimal tool chain (speech_script, text_to_speech,

text_to_dialogue, speech_to_speech, voice_clone, speech_to_text, sound_effects, audio_voice_isolation, audio_process, or audio_stem_separation). Keep distinct steps in one local ledger.

  1. Make a best-effort non-billable beatra.installations.register on first use

or version upgrade (registration failure never blocks work).

  1. Cast and maintain voices live: call beatra.voices.list using any of its 11

dimensions (category, language, gender, age_group, use_case, emotion, supports_context, supports_direction, supports_performance_tags, supports_dialogue, supports_speech_to_speech), confirm status == "ready" and exact compatible_models, audition free via returned preview_url or beatra.voices.preview ({"voice_id": "..."}), and maintain saved voices with non-billable beatra.voices.update. Never name voices, models, or prices before live lookup returns.

  1. Query beatra.models.list with exact capability keys ({"capability": "..."}

— never pass dimensions on models.list; for audio_stem_separation, read pricing[].dimensions.stem_mode from the returned card). Never expose upstream vendor names, internal model IDs, or hardcoded credit numbers.

  1. Prepare and preflight accurately:
  • Smart Voice Director (`beatra.speech.prepare_script`): check

{"capability": "speech_script"} and approve its six-field card first. Inspect directed and scripts[]: pass scripts[i].synthesis unchanged plus a fresh client_request_id to synthesis, and resolve synthesis: null via warnings. Re-calling within 48 hours with exact same input/instructions/language/context changing only voice/model recompiles at zero extra charge (balance cover & max-2 concurrency still apply; never claim prepare_script is generally free).

  • Free preflight: run beatra.speech.validate before speech.synthesize

and beatra.speech.validate_dialogue before speech.synthesize_dialogue to verify estimated_duration_seconds and controls at zero cost.

  • Free aligned subtitles: pass subtitle_enable: true on

speech.synthesize / speech.synthesize_dialogue (NEVER subtitles), and use subtitles: true on audio.transcribe.

  1. Apply the confirmation rule honestly:
  • A well-specified single text_to_speech request—final text, a voice or

selection criteria, and any named format or control—authorizes that one synthesis call; show the six-field production card (Route & Model, Exact Scope, Price & Basis, Duration / Quantity, Pay Mode & Call Count, and If stop detailing free deliverables kept at zero extra charge) alongside the delivery without asking twice.

  • Obtain explicit approval on the six-field card BEFORE calling

prepare_script, synthesize_dialogue, speech.convert, voices.clone, voices.activate, voices.delete, audio.transcribe, audio.generate_sfx, audio.process (isolate_voice, normalize_loudness, trim, loop, fade, convert_format, separate_stems), pilots, or batch remainders. Price questions, comparisons, drafts, general "handle it" prompts, or unfrozen batches are never approval. Use the bundled scripts/mcp_client.py for every Beatra operation:

text
python3 scripts/mcp_client.py call <tool-name>

Pass one JSON object to standard input, and use python3 scripts/mcp_client.py upload <path> --mime-type <exact MIME> for local audio. Store the local ledger and unique opaque client_request_id before sending, poll only the returned task_id via beatra.tasks.get, run finishing calls (normalize_loudness, trim, etc.) one call at a time, lead the reply with the deliverable the user asked for, and report only returned tool and billing facts.

Never configure or call a host Beatra Connector. Never use REST/OpenAPI as a fallback, never imitate the upload protocol, and never call any paid audio finishing or processing step free.

Dialogue, voice conversion, transcription, SFX, and audio processing

  • Multi-speaker dialogue (`beatra.speech.synthesize_dialogue`): check

{"capability": "text_to_dialogue"} and verify each turn's voice supports dialogue (supports_dialogue / supports_context). Validate free with beatra.speech.validate_dialogue, show the six-field card, and pass turns: [{"voice": "...", "text": "..."}] + optional subtitle_enable: true.

  • Speech-to-speech (`beatra.speech.convert`): check

{"capability": "speech_to_speech"} and verify target voice has supports_speech_to_speech: true. Confirm source-speaker permission, pass `audio` (not source), optional remove_background_noise, stability, similarity_boost, style, use_speaker_boost.

  • Transcription (`beatra.audio.transcribe`): check

{"capability": "speech_to_text"}; pass `audio` (not source), subtitles: true (when SRT/VTT requested), diarize, num_speakers, tag_audio_events, and optional language.

  • Sound effects (`beatra.audio.generate_sfx`): check

{"capability": "sound_effects"}; pass prompt, optional duration_seconds, loop, prompt_influence, format.

  • Audio processing (`beatra.audio.process`): always pass `source` (NEVER

audio):

  • isolate_voice: {"capability": "audio_voice_isolation"}, 4.6 s - 5 min,

<= 100 MB. Cleans noisy clone samples or voice recordings.

  • normalize_loudness (present strictly as loudness normalization, never free or a mastering service),

trim, loop, fade, convert_format: {"capability": "audio_process"}, <= 60 min, <= 300 MB, output >= 1 s, 50 calls/day; serialize one finishing job at a time.

  • separate_stems: {"capability": "audio_stem_separation"} (no

dimensions param on models.list; read pricing[].dimensions.stem_mode), <= 10 min, <= 100 MB, 20 calls/day.

Three-route cloning and mandatory confirmations

  1. Mandatory Confirmation 1 (`beatra.voices.clone`): confirm plain consent

before any sample upload; inspect live {"capability": "voice_clone", "include_activation_required": true} cards without vendor names or internal IDs (fast everyday auto ready at once; 10-language expressive ready at once; or two-step trial-then-activate ending in pending_activation); offer paid isolate_voice pre-clean if noisy; approve the six-field card before voices.clone. Spoken proof is always a separate validated TTS workflow.

  1. Mandatory Confirmation 2 (`beatra.voices.activate`): when

status == "pending_activation", inspect returned activation.quote (or tokenless re-quote passing BOTH voice_id and client_request_id without confirmation_token), present the six-field activation card, wait for explicit confirmation, then submit confirmation_token, confirm_credits, and client_request_id. On 24-hour expiry (price_confirmation_required), re-quote free before re-confirming.

  1. Mandatory Confirmation 3 (`beatra.voices.delete`): confirm explicit

intent first, call tokenless {"voice_id": "..."}, relay Beatra's warning verbatim with confirmation_token, and execute only on explicit final confirmation.

Voice, language, price truth, and recovery

Normalize supplied BCP-47 tags by lowercasing the primary subtag and mapping aliases (nb -> no, tl -> fil; e.g. yue-HK -> yue) against voice.language and voice.languages_supported. Intersect models.list.auto.candidate_order with selected_voice.compatible_models for model: "auto", keeping outside compatible models explicit-only, and calculate speech estimates via estimate_formula, unit_price_credits, scale, and billing_basis: "beatra_weighted_characters" (Han = 2, others = 1).

This is the start of the file. Read the full SKILL.md on GitHub.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
2
7-day trend score
10

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/beatra-ai/beatra-skills/beatra-ai-voice-studio/badge)](https://verified-skill.com/skills/beatra-ai/beatra-skills/beatra-ai-voice-studio)

Something wrong with this skill or its page? Tell us.