Choose a speaking voice, create a custom voice, or restore the previous selection. Compare existing voices through a picker, or switch and hear one voice at a time during a live call.
Choose or design a speaking voice when the user asks for a new, different, custom, invented, or generated voice, or restore the voice used immediately before the current one.
Run score Not tested
See how to installChoose a voice for conversations based on the qualities and accent you want. The skill can select an existing voice, create a new one, or restore the voice selected immediately before the current one. It normally selects one voice. If you explicitly request alternatives, it can offer two or three existing voices for comparison.
Use it when you want to change the current voice or find one that matches your preferences. If you have no particular direction in mind, it asks whether you want to describe the voice or leave the choice to the agent. During a live call, it selects and switches to one voice at a time so you can hear it.
Requires muse.voice_options and an environment that supports voice selection and creation. New voices are created one at a time. Multiple options are available only for existing voices, and no option list is shown during calls. To hear a voice selected in text, start a call.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 24, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Help the user choose a new voice. By default, one result is selected immediately. An explicit request for two or three options returns existing voices without selecting one in text, where the runtime presents a picker. During a live call, the runtime always selects and demonstrates one voice per turn without a picker or spoken list.
Let the user's request lead. If they only say they want a new or custom voice without giving any direction, ask one short question: do they want to describe the voice, or should you pick one for them? Then wait for the answer. Do not start voice design in the background before they answer.
If the user explicitly asks to create multiple new voices, explain that this flow creates one new voice at a time and ask which one to start with. Do not silently replace requested new designs with existing library voices.
Ask at most once. If the user gives any usable direction, says "surprise me," or asks you to choose, proceed without another question or confirmation.
If the user asks to restore the immediately previous completed voice selection,
call muse.voice_options once with selection_intent set to previous,
candidate_count set to one, and both allow_create_new_voices and
require_new_voice set to false. Do not infer or copy a voice name.
If the user limits the choice to saved voices without naming one, do not call
muse.voice_options; ask which saved voice they mean. One exact named saved
voice uses the direct switch path.
For every other request admitted here, call muse.voice_options exactly once
with selection_intent set to choose and the complete request.
allow_create_new_voices as permission, not your choice of outcome.
Set it to true when the user permits creating a custom voice, including
requests to create, design, invent, or generate one, or hands you the open
choice with "pick one for me" or "surprise me." The runtime still chooses an
existing system catalog voice when it is the best fit.false when the user restricts the choice to existing system
catalog voices.candidate_count to an explicitly requested two or three, and use three
for "a few." Otherwise use one. Counts above one return existing system
catalog voices only and do not select, save, or switch, so set both creation
fields to false.candidate_count one, set require_new_voice to true only when the
user explicitly requires a newly created voice. Preserve true when their
current reply answers your immediately preceding clarification about a
request to create, design, invent, generate, or make a custom or brand-new
voice. For example, "surprise me" after "make a brand-new voice" still
requires a new design. Set it to false for an open request to pick a
different voice, where the runtime may choose a strong library match.gender to current unless the user explicitly asks for a feminine,
masculine, or neutral acoustic presentation; then use F, M, or N.gender to any when the user explicitly permits any gender or asks to
change gender without naming a target presentation.accent only when the user explicitly requests one of the listed
catalog labels. If no label matches, omit accent; the complete request text
still reaches selection and design. Never infer gender or accent from the
user, persona, avatar, locale, ethnicity, or other demographics.request, including preferences
established by the immediately preceding exchange.Preserve every explicit attribute in the immediate request. The runtime supplies the current voice, available library, and bounded persona and avatar context to the selector. Do not copy private or unrelated facts into the tool request.
The rewrite service expands a custom request into the detailed acoustic prompt,
conversational instructions, name, and preview text required by the voice model.
Do not write those implementation fields yourself and do not call
muse.design_voice.
Custom design runs in one managed background worker. Briefly say it is being created, then continue normally. Do not poll, retry automatically, or start a second design while it is running.
Follow the tool's authoritative result:
options_presented, include widget.embed_token exactly once when the
result contains one; otherwise the picker is already on screen. Ask the user
to choose without enumerating the options or claiming anything was selected,
saved, or switched.options, name the returned voices and ask the user to choose. This is a
compatibility fallback when interactive presentation is unavailable.live_switch_completed is
true, then invite the caller to change it again if they want.Refer to voices only by display name. Never expose voice, saved-voice, profile, call, or worker identifiers. Do not create chat preview UI yourself.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create a 3D object with three.js, inspect it from every angle in an interactive viewer, and download it as OBJ + MTL or GLB for use in other 3D applications.
Maintain a private task list with deadlines, next steps, waiting parties, and blockers. Update progress and dependencies, merge duplicate items, and archive closed tasks so ongoing commitments stay clear and easy to follow.
Coordinate a task from a verifiable goal through completion. Handle work directly or split independent tasks across separate agent sessions, track progress, verify results, and arrange pull request merging when included in the goal.
Create animated HTML pages with smooth scene transitions and playback controls. An editable timeline lets users adjust scene lengths and speeds, with fixed landscape or portrait layouts prepared for video export.
Review synced Apple Health records, including steps, heart rate, sleep, and workouts. Retrieve daily summaries or detailed samples for a chosen period, and check sync status and missing data before interpreting the results.
Create and edit Word documents and templates, reorganize text, replace images, and work with tracked changes or comments. Apply proper headings and lists, then render every page to check its appearance before delivery.