skills.rest
opensquilla
opensquillaOFFICIAL
Explore all skills by this author →
WebsiteGitHub

voiceover-studio

Generate TTS voiceover audio from scripts using configured audio providers and voice search.

6.8k|540|Updated May 6, 2026
Search Tags:#audio generation#tts#narration#VoiceOver#text to speech#voice search#配音
One-click install
npx skills add https://github.com/opensquilla/opensquilla --skill voiceover-studio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: voiceover-studio
Source: https://github.com/opensquilla/opensquilla/tree/main/src/opensquilla/skills/bundled/voiceover-studio
Command: npx skills add https://github.com/opensquilla/opensquilla --skill voiceover-studio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turning written scripts into spoken audio requires picking the right voice, locale, and accent, and naive TTS calls often produce mismatched accents or unusable output. This Skill routes text-to-speech requests through OpenSquilla's audio tools with locale-aware voice selection and preview-first generation.

Core Features & Use Cases

  • Locale-aware voice selection: Searches for voices matching the target language, locale, and accent (e.g., zh-CN Mandarin, en-GB British) before calling the TTS tool.
  • Preview-first workflow: Generates a short sample for voice approval before committing to long batch narration.
  • Batch narration: Splits long scripts into natural paragraphs under provider limits and produces stable output filenames.
  • Use Case: A creator has a short-video script with VOICEOVER lines in Mandarin. The Skill searches for a Mandarin-capable voice, generates a one-paragraph preview, and after approval produces the full playable audio artifact.

Quick Start

Generate a Mandarin voiceover audio file from my video script using a natural female narrator voice.

Frequently Asked Questions about voiceover-studio

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a script to voiceover audio with TTS?▼

Provide the script text and target language, and the Skill searches for a matching voice, generates a short preview sample, then produces the full audio via the tts tool. Long scripts are split into natural paragraphs under provider limits.

How do I choose the right voice for Chinese or accented English TTS?▼

The voice_search tool is called with the target language, locale, and accent, such as language=zh with Mandarin accent or language=en with British accent. The matching voice_id is then passed to the tts call instead of falling back to a default English voice.

Can I clone a celebrity or public figure voice for narration?▼

No. The Skill does not clone or mimic public figures, private persons, or copyrighted character voices. Requests like that are converted into non-identifying traits such as age range, energy, pacing, timbre, and emotion.

Why does TTS return not_available and how is it handled?▼

A not_available result includes a note distinguishing provider configuration issues, missing voice IDs, language mismatches, and provider errors. The Skill quotes that note and may call audio_provider_capabilities or retry voice_search with a broader locale.

Does the TTS workflow support batch generation for long scripts?▼

Yes. Long text is split into natural paragraphs under the provider limit and generated with stable filenames. A preview of the first paragraph is created first unless the user explicitly needs the full asset immediately.

Related Skills

Explore More Content & Communication Skills→
spindle79spindle79

prose-for-speech

Rewrites punctuation and spacing in scripts for natural TTS delivery.

Community
Intermediate
vercel-labsvercel-labs
15.9k

remotion

Convert JSON timeline specs into playable Remotion video compositions.

Official
Intermediate
GetFresh-VenturesGetFresh-Ventures

voice-synth

Convert written briefs into TTS scripts with pronunciation guides and pacing markers.

Official
Intermediate
FutureAtomsFutureAtoms
1

livekit-tts

Configure multi-provider TTS models for LiveKit agents with voice customization.

Community
Advanced