{"id":51160930,"url":"https://github.com/longlannet/edge-tts","last_synced_at":"2026-06-26T13:30:36.316Z","repository":{"id":363000141,"uuid":"1220635829","full_name":"longlannet/edge-tts","owner":"longlannet","description":"OpenClaw skill for Microsoft Edge TTS with Telegram OGG/Opus voice-note output","archived":false,"fork":false,"pushed_at":"2026-06-06T22:41:35.000Z","size":8,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-07T00:13:45.152Z","etag":null,"topics":["agentskill","edge-tts","openclaw","telegram","text-to-speech"],"latest_commit_sha":null,"homepage":"https://github.com/longlannet/edge-tts","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/longlannet.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-25T06:07:00.000Z","updated_at":"2026-06-06T22:41:38.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/longlannet/edge-tts","commit_stats":null,"previous_names":["longlannet/edge-tts"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/longlannet/edge-tts","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/longlannet%2Fedge-tts","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/longlannet%2Fedge-tts/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/longlannet%2Fedge-tts/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/longlannet%2Fedge-tts/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/longlannet","download_url":"https://codeload.github.com/longlannet/edge-tts/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/longlannet%2Fedge-tts/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34819597,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-26T02:00:06.560Z","response_time":106,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentskill","edge-tts","openclaw","telegram","text-to-speech"],"created_at":"2026-06-26T13:30:35.709Z","updated_at":"2026-06-26T13:30:36.306Z","avatar_url":"https://github.com/longlannet.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# edge-tts\n\n面向 OpenClaw 的文字转语音 skill，使用 Microsoft Edge 在线语音服务生成音频。\n\n基于 Python 包 [`edge-tts`](https://github.com/rany2/edge-tts)。\n\n## 它能做什么\n\n- 把文字生成语音文件\n- 默认使用中文女声 `zh-CN-XiaoxiaoNeural`\n- 支持指定 Edge Neural voice\n- 输出 `MEDIA:/path/to/file`，方便 OpenClaw 自动发送音频\n- Telegram 语音泡泡默认使用 `.ogg` / Opus 格式\n\n## 安装\n\n```bash\nbash scripts/install.sh\n```\n\n## 校验\n\n```bash\nbash scripts/check.sh\n```\n\n## 常用命令\n\n```bash\n./venv/bin/python scripts/speak.py \"你好，我是小珍。\"\n./venv/bin/python scripts/speak.py \"Hello from OpenClaw.\" --voice en-US-AriaNeural\n./venv/bin/python scripts/speak.py \"语速快一点。\" --rate +10%\n./venv/bin/python scripts/speak.py \"Telegram 语音测试。\" --voice-note\n./venv/bin/edge-tts --list-voices\n```\n\n## Telegram 语音泡泡\n\n如果是在 Telegram 里发送“语音消息 / 语音泡泡 / voice note”，默认使用：\n\n```bash\n./venv/bin/python scripts/speak.py \"要说的话\" --voice-note\n```\n\n`--voice-note` 会生成 `.ogg` 文件，并用 Opus 编码，这是 Telegram 原生语音泡泡最稳的格式。普通音频文件才使用默认 `.mp3`。\n\n## 输出规则\n\n`scripts/speak.py` 成功后会打印：\n\n```text\nMEDIA:/absolute/path/to/audio.mp3\n```\n\n在 OpenClaw 对话里，生成成功后直接回复 `NO_REPLY`，让系统自动发送音频；不要再额外调用消息工具发送同一个文件。\n\n## 说明\n\n- 需要联网访问 Microsoft Edge TTS 服务。\n- 生成 `.ogg` / Opus 语音泡泡需要本机安装 `ffmpeg`。\n- `venv/` 是本地虚拟环境，`media/` 是生成音频目录，二者不会提交到仓库。\n- 如果环境异常，重新运行 `scripts/install.sh`。\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flonglannet%2Fedge-tts","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flonglannet%2Fedge-tts","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flonglannet%2Fedge-tts/lists"}