reading-text-aloud
Skill0 starsChanged 9 days agoMITView on GitHub
Turns text into spoken audio in the user's VoiceLabs voices and hands back the audio link. Use when the user asks to 'read this paragraph in my Narrator voice', 'narrate these five sections', 'make a voiceover', 'convert this text to speech', 'generate an audio version', 'say this in my voice', or wants text to speech (TTS) for a script. Generation is metered by the user's plan.
In this repository66 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adding-uptime-monitorsSkill
- analyzing-page-performanceSkill
- booking-meetingsSkill
- building-onboarding-workflowsSkill
- building-study-guidesSkill
- capturing-tasksSkill
- capturing-web-pagesSkill
- chasing-unpaid-invoicesSkill
- checking-domain-connectionsSkill
- checking-email-deliverabilitySkill
- checking-notification-deliverySkill
- checking-uptime-statusSkill
- cleaning-up-bookkeepingSkill
- connecting-customer-domainsSkill
- discussing-buildsSkill
- drafting-invoicesSkill
- drafting-social-postsSkill
- editing-demosSkill
- editing-page-draftsSkill
- extracting-document-textSkill
- finding-meeting-timesSkill
- handling-flaky-changesSkill
- investigating-tasksSkill
- making-demo-videosSkill
- managing-bookingsSkill
- managing-content-calendarSkill
- managing-demosSkill
- managing-voice-librarySkill
- planning-revisionSkill
- preflighting-domainsSkill
- publishing-pagesSkill
- reading-financial-reportsSkill
- reading-web-pagesSkill
- reporting-snapvisor-usageSkill
- researching-course-materialSkill
- researching-summary-librarySkill
- responding-to-incidentsSkill
- reviewing-email-performanceSkill
- reviewing-notification-workflowsSkill
- reviewing-social-performanceSkill
- reviewing-visual-buildsSkill
- reviewing-workloadSkill
- searching-getitdone-api-docsSkill
- sending-email-campaignsSkill
- sending-notificationsSkill
- setup-bioflowSkill
- setup-calySkill
- setup-demofySkill
- setup-dodomainSkill
- setup-getitdoneSkill
- setup-notiflySkill
- setup-postifySkill
- setup-sendlySkill
- setup-shortySkill
- setup-snapvisorSkill
- setup-superbooksSkill
- setup-unotesSkill
- setup-upapiSkill
- setup-uptimelySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 0 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Every tool in this skill comes from the voicelabs MCP server, the VoiceLabs connector, and is written here as voicelabs:<tool>.
- Very specific: line 15
Tools listed by name: call them directly, for example voicelabs:list_voice_profiles.
- Very specific: line 31
If the account has no voices, or voicelabs:speak returns NOT_FOUND, offer a built-in preset: call voicelabs:ensure_voice_profile with a …
- Very specific: line 32
Call voicelabs:speak with the text and the voice.
- Very specific: line 33
Call voicelabs:get_generation with that id.
- Very specific: line 38
Call voicelabs:search_tools first to get the exact declarations, then start every part at once.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Generated from plugins/voicelabs/skills/reading-text-aloud/SKILL.md by scripts/sync-skills.mjs. Edit the plugin copy, then run the script. -->Read text aloud with VoiceLabs
Generate speech from the user's text in one of their voice profiles, wait for it to finish, and give them the audio link.
Connecting and calling the tools
Every tool in this skill comes from the voicelabs MCP server, the VoiceLabs connector, and is written here as voicelabs:<tool>. The server lists the named tools and the Code Mode pair side by side.
- Tools listed by name: call them directly, for example
voicelabs:list_voice_profiles. - Several operations in one round trip, or a named tool is missing: call
voicelabs:search_toolsfirst, then call each tool insidevoicelabs:execute_typescriptasexternal_<tool>(for exampleexternal_list_voice_profiles); the program mustreturnits result. Scopes, confirmations and gates are identical on both surfaces. - "Tool not found": switch to the Code Mode route instead of retrying the direct call. If
voicelabs:search_toolsdoes not return the tool either, its OAuth scope was not granted; the user reconnects VoiceLabs and approves that scope. - No
voicelabstools at all: VoiceLabs is not connected yet. Follow thesetup-voicelabsskill.
Tools you will use
voicelabs:list_voice_profiles: the account's voices with id, name, language,voice_type(preset or cloned) and engine.voicelabs:ensure_voice_profile: make sure a named voice exists, creating it from a built-in preset if it does not. Safe to repeat.voicelabs:speak: start a generation fromtextwithprofileIdorprofileNameand optionallanguage. ReturnsgenerationIdwith statusgenerating.voicelabs:get_generation: poll a generation; returnsstatus(generating,completed,failed) and, once completed,audioUrl.voicelabs:search_toolsandvoicelabs:execute_typescript: start several generations in one round trip for multi-part scripts.
Workflow
- Pick the voice. If the user named one, pass it as
profileName. Otherwise callvoicelabs:list_voice_profilesand ask which voice, or suggest one that matches the text's language. - If the account has no voices, or
voicelabs:speakreturnsNOT_FOUND, offer a built-in preset: callvoicelabs:ensure_voice_profilewith a name such as "Narrator" and use the id it returns. - Call
voicelabs:speakwith the text and the voice. Keep thegenerationId. - Call
voicelabs:get_generationwith that id. While the status isgenerating, call it again. When it iscompleted, give the user theaudioUrl. If it isfailed, report theerrorfield. - For a long script, split it at paragraph or section breaks and generate each part (see below). Return the links in order, labelled by section.
Several parts in one round trip
Call voicelabs:search_tools first to get the exact declarations, then start every part at once. Do not wait for audio inside the sandbox; return the ids and poll voicelabs:get_generation afterwards.
const parts = ["Section one text", "Section two text"];
const started = await Promise.all(
parts.map((text) =>
external_speak({ text, profileName: "Narrator" }).catch((e) => ({ error: String(e) })),
),
);
return started; // generationId per part, or "<CODE>: <details>"Rules
- Speak only the text the user gave or approved. Do not add intros, disclaimers, or extra lines.
- Audio links expire after about 15 minutes. If the user comes back later, call
voicelabs:get_generationagain for a fresh link. QUOTA_EXCEEDED: the account's allowance for the period is used. Relay the message as written and stop; do not push a plan or retry.RATE_LIMITED: wait theretryAfterSecondsit names, then continue.SCOPE_MISSING: the connection lacksvoice:generate; the user can reconnect and grant it.- Arguments are strict and camelCase (
profileId, notprofile_id).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

