kejilion/ai-skills/telegram-voice-tts
Claude Code and agent skill by kejilion/ai-skills
- community
Checking that the SKILL.md file is still in the repository.
Generate high-quality Telegram voice notes (bubbles) using Microsoft Edge TTS and FFmpeg. Use when asked to send audio as a voice message, or when the user requires voice-bar replies instead of audio files. Handles edge-tts generation and OGG/Opus conversion for native Telegram voice compatibility.
Install
npx vskill@latest install kejilion/ai-skills/telegram-voice-ttsSKILL.md
Telegram Voice TTS
⚠️ Deprecated / 备用方案:OpenClaw 已内置 Edge TTS(免费、无密钥),默认可用且会自动生成语音气泡。推荐直接使用内置 TTS。仅当内置 TTS 异常时,才使用本技能脚本手动生成语音。
This skill provides a workflow for generating native Telegram voice notes.
Workflow
- Use
scripts/telegram_voice.pyto generate an OGG/Opus file:
``bash python3 scripts/telegram_voice.py "Text to speak" "path/to/output.ogg" ``
- Send the resulting file using the
messagetool:
- Set
asVoice: true - Include
[[audio_as_voice]]in the message text - Provide the local
filePathto the OGG file
Requirements
edge-tts(Python package)ffmpeg(System binary)
推荐:OpenClaw 内置 Edge TTS 配置手册(无需本技能)
内置 TTS 支持 Edge/OpenAI/ElevenLabs,未配置 API key 时默认用 Edge TTS(免费)。在 Telegram 自动发语音气泡。
快速启用(Edge TTS)
⚠️ 重要:Edge TTS 在 OpenClaw 内部的 provider id 是microsoft(非edge)。顶层provider可以写"edge"(会自动映射),但providers下的配置 key 必须用 `microsoft`,否则 voice/lang 等参数不会生效,会回退到默认英文音色en-US-MichelleNeural。
方法一:命令行配置(推荐)
方法二:手动编辑配置文件
编辑 /root/.openclaw/openclaw.json(或对应主机配置),在 messages.tts 下设置:
然后重启 Gateway:
之后 直接发送文字回复 即可,内置会自动附带语音气泡。切勿再手动调用 tts 工具,以免重复发送两条音频。
常见中文音色
| Voice ID | 性别 | 风格 | |
|---|---|---|---|
zh-CN-YunyangNeural | 男 | 新闻播报、沉稳 | |
zh-CN-XiaoxiaoNeural | 女 | 温暖、日常 | |
zh-CN-YunxiNeural | 男 | 年轻、活力 | |
zh-CN-XiaoyiNeural | 女 | 活泼、轻快 |
完整列表:edge-tts --list-voices | grep zh-CN
如果要改用 OpenAI / ElevenLabs(可选)
- 设置环境变量或在配置里填入 API key:
OPENAI_API_KEY或ELEVENLABS_API_KEY- 然后改
provider为openai或elevenlabs。未配置时会自动回落到 Edge。
常见问题
- 语音是英文? 检查配置 key 是否写成了
providers.edge——必须是providers.microsoft。OpenClaw 内部 Edge TTS 注册为microsoftprovider。 - 为何用 MP3 也有语音气泡? Telegram
sendVoice支持 OGG/Opus/MP3/M4A,OpenClaw 会按文件扩展名判断为语音消息。 - Edge TTS OGG/Opus 失败? 部分
ogg-*opus格式 Edge 服务不支持,会回退 MP3。使用上面的 MP3 配置最稳定。 - 重复发送两条语音? 把
messages.tts.auto设为always后,不要再手动调用tts工具,只发文字即可。
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpublic/telegram-voice-tts/SKILL.md
Popularity
- Repository stars
- 88
- Repository forks
- 29
- 7-day trend score
- 22
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 21 Sep 2026, a month ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kejilion/ai-skills/telegram-voice-tts)