← Back to Skills Marketplace
338
Downloads
0
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install voice-reply-mode
Description
Enables agents to reply in the same modality as received: voice messages get voice replies, text messages get text replies, using Edge TTS and config snippets.
Usage Guidance
This skill appears to do what it says: package workspace snippets, gateway config examples, and a small helper script to call an external 'edge-tts' CLI. Before installing or enabling it: 1) Verify you have a trusted 'edge-tts' binary installed (the skill calls edge-tts but does not install or declare it). 2) Review the gateway config snippet and only allow the skill/agent to patch gateway settings if you trust it—changing messages.tts.auto to 'inbound' can alter behavior platform-wide. 3) Inspect the included scripts (scripts/edge-tts.sh) locally to confirm they match your expectations. 4) Test in a staging environment (one agent workspace and one channel) before rolling out. If you need higher assurance, request the skill author or publisher metadata/homepage and an explicit dependency list for edge-tts.
Capability Analysis
Type: OpenClaw Skill
Name: voice-reply-mode
Version: 1.0.0
The skill is designed to enable modality-matching behavior (voice-to-voice and text-to-text) for agents using Edge TTS. It contains a straightforward shell script (scripts/edge-tts.sh) for generating audio and several documentation files (SKILL.md, gateway-config.md) providing configuration snippets and deployment notes for platforms like Telegram and Feishu, with no signs of malicious intent or unauthorized data access.
Capability Assessment
Purpose & Capability
Name/description, workspace snippets, gateway config examples, and a small helper script all align with enabling same‑modality replies. The included artifacts (IDENTITY/SOUL/TOOLS snippets, gateway examples, and a TTS helper script) are appropriate for this purpose.
Instruction Scope
SKILL.md stays within scope: it instructs the operator to copy snippets into a workspace and only to patch gateway config if the user explicitly asks. It references using the 'edge-tts' CLI for TTS generation; however, the skill does not declare or provide an installer for that dependency—so the agent's runtime must already have edge-tts available or the operator must install it manually.
Install Mechanism
This is an instruction-only skill with no install spec and a tiny helper script. Nothing is downloaded from arbitrary URLs and no archives are extracted. Risk from install mechanism is low.
Credentials
The skill requests no environment variables, no credentials, and no config paths. The content uses only local files and a local CLI ('edge-tts'); there are no unexpected credential accesses.
Persistence & Privilege
always is false and the skill does not request persistent or system-wide privileges. It documents a workflow that may patch gateway config, but only if explicitly authorized by the user; this is appropriate but operator caution is recommended before applying gateway changes.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install voice-reply-mode - After installation, invoke the skill by name or use
/voice-reply-mode - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Voice Reply Mode（语音对语音 / 文本对文本）
让 agent 实现：语音进 → 语音出，文字进 → 文字出。
包含工作区行为规则（SOUL/IDENTITY/TOOLS 片段）、Edge TTS 辅助脚本、以及 messages.tts 网关配置示例。
适用于 Telegram / 飞书语音消息场景，按文档复制配置即可启用同模态回复。
使用步骤
1. 阅读 references/workspace-snippets.md 与 references/gateway-config.md
2. 将片段写入目标 agent 的 SOUL.md / IDENTITY.md / TOOLS.md
3. 如需自动语音回复，设置网关：messages.tts.auto = inbound
4. 用 一条文字 + 一条语音 验证效果
───
Voice Reply Mode (Same‑Modality Reply)
Enables voice‑in → voice‑out, text‑in → text‑out behavior for agents.
Includes workspace behavior snippets (SOUL/IDENTITY/TOOLS), an Edge TTS helper script, and gateway config examples for messages.tts.
Designed for Telegram/Feishu voice‑note workflows—copy the snippets and it just works.
Quick Steps
1. Read references/workspace-snippets.md and references/gateway-config.md
2. Copy snippets into the target agent’s SOUL.md / IDENTITY.md / TOOLS.md
3. For auto voice replies, set messages.tts.auto = inbound
4. Validate with one text + one voice message
Metadata
Frequently Asked Questions
What is Voice Reply Mode?
Enables agents to reply in the same modality as received: voice messages get voice replies, text messages get text replies, using Edge TTS and config snippets. It is an AI Agent Skill for Claude Code / OpenClaw, with 338 downloads so far.
How do I install Voice Reply Mode?
Run "/install voice-reply-mode" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Voice Reply Mode free?
Yes, Voice Reply Mode is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Voice Reply Mode support?
Voice Reply Mode is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Voice Reply Mode?
It is built and maintained by nasplycc (@nasplycc); the current version is v1.0.0.
More Skills