All skills
hypit-ai avatar

/hypit

@04405de
by Hypit.AIhypit-ai/hypit18k stars
2,113

Direct and produce videos with Hypit, primarily through generated media and authored components while incorporating briefs, references or supplied material; includes SVML/SVS/SVRun authoring and Runtime or credential setup.

Use this Skill: https://skilld.dev/gh/hypit-ai/hypit/hypit

This session only. Nothing lands on disk.

referencesplaybookscraftvoice-direction.md

≈1.6k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Directing a voice

Read this before choosing, designing or changing a character's voice, including when adapting a production with an existing Voice Reference. Cast a voice the audience will want to keep hearing. For creator-led social video, favor a distinctive, engaging presence that makes the words feel addressed to someone.

Cast the person through the sound

Imagine a voice worth hearing: who is speaking, whom they are addressing, and what makes the sound appealing for this character. A playful little creature with a sweet, bright voice or a storyteller with a rounded, resonant voice suggests sound as well as personality. A role such as founder or creator supplies context; still choose what this particular person sounds like. "An unexpected voice" describes its relationship to the casting. Name the appealing sound chosen for that relationship so the voice model has a vocal character to realize.

As in Image direction, use high-level language that carries sensory information, then make the decisive qualities specific. "Magnetic" states the desired appeal; a clear, youthful tone and nimble, teasing phrasing begin to express it. Pitch, vocal weight, brightness, softness or grain are casting choices, not interchangeable words for a good voice. A lightly husky voice has a particular texture; choose it when that texture belongs to the person. Let the intended encounter guide the presence, from a lively recommendation to an intimate conversation.

Look at the character reference and use the Brief to make the casting choice. A supplied voice can establish an exact identity. An existing project's voice can continue that identity when its casting still serves the new piece. For a new person or character, develop the voice that makes this role worth following. Keep the casting choice and the reference's role in Treatment and Source.

Compress the voice into a vivid direction

A useful voice description is often one short paragraph: a recognizable vocal character, the sound qualities that make it appealing, and a characteristic way of addressing someone. Age and gender presentation, language or accent, pitch, texture and articulation can sharpen that impression. Choose the few that settle the casting; this is not a field list to fill out. Cultural or character shorthand earns its place through the sound it evokes.

Translate the character's role in the piece into audible qualities. Wanting the viewer to trust a claim can inform clear articulation and thoughtful emphasis; the request should carry that chosen sound and manner of speaking. Music, graphic reveals and the later mix receive their own direction. Direction and its inputs explains this relationship between the whole design and the individual request.

For example:

A young woman's sweet, clear voice with a bright upper register and a light, smooth tone.
Conversational American English, nimble and playful, like a friend excited to let you in on a find.
Her curiosity lifts a question; an audible smile gives her confident answers warmth.

A different character can have a different kind of appeal:

A mature man's rounded, resonant mid-low voice with clear, relaxed British English. He sounds
thoughtful and approachable, carefully weighing an idea with someone across the table. Measured
phrasing and purposeful emphasis give his judgments conviction.

The first direction chooses a light, playful appeal; the second chooses warmth and considered conviction. Vocal pitch and delivery pace do different work: a high voice can be unhurried, and a low voice can speak nimbly. Preserve the qualities that define the casting while choosing the language and delivery density the actual work needs.

Let the sample carry the character

When choosing or designing a sample, prefer the performed language and a delivery compatible with the new piece when available. A sample carries pronunciation and phrasing cues as well as timbre; cross-language identity transfer does not by itself establish the target accent or cadence. Preserve a supplied identity and direct those target-language qualities explicitly in the requests.

Choose a short, natural line that gives the intended voice room to show itself. A curious question followed by a pleased response can demonstrate a lively character: "Wait, you did all that with one photo? Okay, now you've got my attention." A considered observation can suit the second casting. The line should make the intended manner useful to the thought, rather than merely name the product. Write the intended pronunciation for unfamiliar names in Script before using the line as a sample.

Voice Design turns that short line into a reusable Voice Reference. A speaking-video model can use it while performing the finished Script; a passage built around independent narration can use the same reference through Voice Clone. The casting line and the finished passage have different jobs. Voice and performance owns reference preparation, reuse and that performance choice; the selected model's package documentation owns its exact inputs.

Let one voice express different thoughts

The reference carries vocal identity and demonstrates a manner of speaking. Each finished passage has its own reason to be spoken: draw someone in, challenge a claim, become delighted by an example, or deliver a confident verdict. Direct those attitudes through the video performance or the selected speech model's available inputs while keeping the same person recognizable. One accepted voice can express different thoughts; recurring identity does not require one fixed emotional state throughout the work.

Video direction connects that attitude to gaze, gesture and interaction. For independent speech, the Script and supported speech-model inputs shape delivery. Choose time from this intended performance using Script measurement. The pace estimate sizes the passage; the voice and performance direction give it character. Fast speech alone does not establish emphasis, changing attitude or expressive intonation.

Source: SKILL.md on GitHub

No alerts8d3 checks · Risk SAFE
  • Gen Agent Trust Hub8d

    The hypit skill provides comprehensive documentation and automation logic for a video production toolchain. It manages environment setup using standard package managers (npm, brew, uv), handles credentials securely through native OS lockers, and executes production builds. Security findings are primarily related to the tool's intended automation capabilities, such as local script execution for web capture and the inherent risk of indirect prompt injection when processing external media links and website content.

  • Socket8d

    No alerts

  • Snyk8d

    Risk: LOW · No issues

Signed by skilld at 04405de. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 13 hours ago.

Activeupdated 2 weeks ago

README badge

README badge for hypit-ai/hypit