Run any Skill in Manus with one click

cadis-voice

Stars55

Forks12

UpdatedApril 26, 2026 at 11:51

Use when implementing or reviewing CADIS voice output, TTS providers, STT, wake word, voice preferences, speech routing policy, auto-speak, voice preview, or RamaClaw voice migration.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

Growth-Circle

Growth-Circle/cadis

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	cadis-voice
description	Use when implementing or reviewing CADIS voice output, TTS providers, STT, wake word, voice preferences, speech routing policy, auto-speak, voice preview, or RamaClaw voice migration.

CADIS Voice

Read First

docs/03_FRD.md
docs/16_CONFIG_REFERENCE.md
docs/22_UI_STATE_PROTOCOL_CONTRACT.md
docs/23_UI_DESIGN_SYSTEM.md

Rules

Voice is controlled by daemon policy and content kind.
Do not speak long code, diffs, terminal logs, or raw test output.
Approval speech is a short risk summary only.
Voice preview must be cancellable.
Voice settings persist through CADIS config.
Node-based Edge TTS can be an optional compatibility path, not core daemon dependency.

Initial Voice Preferences

voice_id
rate
pitch
volume
auto_speak
provider
max_spoken_chars

Validation

Preview start, stop, success, and failure.
Auto-speak final response only.
Speech routing by content kind.
Redaction before speech if sensitive data is possible.

Use installed speech and transcribe skills when the task involves audio workflows.

More from this repository

same repository

cadis-model-provider

Growth-Circle/cadis

Use when implementing or reviewing CADIS model provider traits, provider capabilities, streaming responses, tool-call support, OpenAI, Ollama, Anthropic, Gemini, OpenRouter, LM Studio, or custom HTTP providers.

2026-04-2655

cadis-open-source

Growth-Circle/cadis

Use when updating CADIS contributor docs, release docs, changelog, GitHub issue templates, PR templates, CI, README, governance, license notices, or project planning documents.

2026-04-2655

cadis-policy-security

Growth-Circle/cadis

Use when implementing or reviewing approval policy, risk classes, sandbox rules, secret redaction, tool permissioning, threat model, or security-sensitive behavior.

2026-04-2655

cadis-protocol

Growth-Circle/cadis

Use when changing CADIS protocol messages, event schemas, content routing, HUD protocol, approval payloads, model catalog events, or compatibility rules.

2026-04-2655

cadis-ramaclaw-ui

Growth-Circle/cadis

Use when implementing or reviewing CADIS HUD, RamaClaw UI adaptation, config window, agent rename, theme picker, voice/model settings, orbital HUD, approval cards, screenshot parity, or desktop window behavior.

2026-04-2655

cadis-rust-core

Growth-Circle/cadis

Use when implementing or reviewing CADIS Rust workspace structure, cadisd daemon, cadis CLI, session core, event bus, store, or core crate boundaries.

2026-04-2655

name	cadis-voice
description	Use when implementing or reviewing CADIS voice output, TTS providers, STT, wake word, voice preferences, speech routing policy, auto-speak, voice preview, or RamaClaw voice migration.

CADIS Voice

Read First

docs/03_FRD.md
docs/16_CONFIG_REFERENCE.md
docs/22_UI_STATE_PROTOCOL_CONTRACT.md
docs/23_UI_DESIGN_SYSTEM.md

Rules

Voice is controlled by daemon policy and content kind.
Do not speak long code, diffs, terminal logs, or raw test output.
Approval speech is a short risk summary only.
Voice preview must be cancellable.
Voice settings persist through CADIS config.
Node-based Edge TTS can be an optional compatibility path, not core daemon dependency.

Initial Voice Preferences

voice_id
rate
pitch
volume
auto_speak
provider
max_spoken_chars

Validation

Preview start, stop, success, and failure.
Auto-speak final response only.
Speech routing by content kind.
Redaction before speech if sensitive data is possible.

Use installed speech and transcribe skills when the task involves audio workflows.