Files
openclaw-skills/categories/speech-and-transcription.md
2026-03-11 16:19:25 +08:00

52 lines
7.4 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# 语音与转录
[← 返回主列表](../README.md#table-of-contents)
**45 个技能**
- [addis-assistant-stt](https://github.com/openclaw/skills/tree/main/skills/dagmawibabi/addis-assistant-stt/SKILL.md) - 提供语音转文本STT与文本处理能力。
- [agent-voice](https://github.com/openclaw/skills/tree/main/skills/nerdsnipe/agent-voice/SKILL.md) - 面向 AI 代理的命令行博客平台。
- [akaunting](https://github.com/openclaw/skills/tree/main/skills/liekzejaws/akaunting/SKILL.md) - 通过 REST API 与 Akaunting 开源会计软件交互。
- [alexa-cli](https://github.com/openclaw/skills/tree/main/skills/buddyh/alexa-cli/SKILL.md) - 通过 `alexacli` CLI 控制 Amazon Alexa 设备和智能家居。
- [announcer](https://github.com/openclaw/skills/tree/main/skills/odrobnik/announcer/SKILL.md) - 通过 Airfoil AirPlay 扬声器在家中播报文本。
- [assemblyai-transcribe](https://github.com/openclaw/skills/tree/main/skills/tristanmanchester/assemblyai-transcribe/SKILL.md) - 使用 AssemblyAI 转录音频/视频。
- [audio-gen](https://github.com/openclaw/skills/tree/main/skills/udiedrichsen/audio-gen/SKILL.md) - 生成有声书、播客或教育音频内容。
- [audio-reply](https://github.com/openclaw/skills/tree/main/skills/matrixy/audio-reply-skill/SKILL.md) - 使用 TTS 生成音频回复。
- [auto-whisper-safe](https://github.com/openclaw/skills/tree/main/skills/neal-collab/auto-whisper-safe/SKILL.md) - Support for memory-safe automatic chunking transcription — can run on a 16GB machine without crashing.
- [brw-de-ai-ify](https://github.com/openclaw/skills/tree/main/skills/brianrwagner/brw-de-ai-ify/SKILL.md) - Remove AI-generated tone and restore a more natural human expression to the text.
- [chichi-speech](https://github.com/openclaw/skills/tree/main/skills/hudeven/chichi-speech/SKILL.md) - 使用 Qwen3 提供高质量文本转语音 RESTful 服务。
- [claw-voice](https://github.com/openclaw/skills/tree/main/skills/niczy) - 你已通过语音连接到一个实时用户会话。
- [clonev](https://github.com/openclaw/skills/tree/main/skills/instant-picture/clonev/SKILL.md) - 使用 Coqui XTTS v2 克隆任意声音并生成语音。
- [critical-article-writer](https://github.com/openclaw/skills/tree/main/skills/tomstools11/critical-article-writer/SKILL.md) - 生成文章草稿与大纲。
- [cult-of-carcinization](https://github.com/openclaw/skills/tree/main/skills/loserbcc/cult-of-carcinization/SKILL.md) - 让你的代理拥有声音——以及听觉。
- [deepdub-tts](https://github.com/openclaw/skills/tree/main/skills/yuval-deepdub/deepdub-tts/SKILL.md) - 使用 Deepdub 生成语音音频并以 MEDIA 格式附加。
- [deepgram](https://github.com/openclaw/skills/tree/main/skills/nerkn/deepgram/SKILL.md) - Deepgram Speech-to-Text 的命令行接口。
- [dellight-cro-revenue-ops](https://github.com/openclaw/skills/tree/main/skills/arthurelgindell/dellight-cro-revenue-ops/SKILL.md) - DELLIGHT.AI 是一家位于迪拜DIFC的人工智能初创公司相关技能。
- [documents-ai](https://github.com/openclaw/skills/tree/main/skills/dbirulia/documents-ai/SKILL.md) - Veryfi 提供的实时 OCR 与数据提取 API。
- [doubao-api-open-tts](https://github.com/openclaw/skills/tree/main/skills/xdrshjr/doubao-api-open-tts/SKILL.md) - 使用豆包(火山引擎)的文本转语音服务。
- [duby](https://github.com/openclaw/skills/tree/main/skills/autogame-17) - 使用 Duby.so API 将文本转换为语音。
- [eachlabs-voice-audio](https://github.com/openclaw/skills/tree/main/skills/eftalyurtseven/eachlabs-voice-audio/SKILL.md) - Using ElevenLabs, Whisper, and RVC for TTS, STT, and voice conversion.
- [easyverein-api](https://github.com/openclaw/skills/tree/main/skills/truefoobar/easyverein-api/SKILL.md) - 集成 easyVerein v2.0 REST API。
- [elevenlabs-agents](https://github.com/openclaw/skills/tree/main/skills/pennyroyaltea/elevenlabs-agents/SKILL.md) - 创建、管理并部署 ElevenLabs 代理。
- [elevenlabs-media](https://github.com/openclaw/skills/tree/main/skills/clawdbotborges) - ElevenLabs 音乐生成技能。
- [elevenlabs-transcribe](https://github.com/openclaw/skills/tree/main/skills/paulasjes/elevenlabs-transcribe/SKILL.md) - 使用 ElevenLabs 将音频转录为文本。
- [elevenlabs-tts](https://github.com/openclaw/skills/tree/main/skills/shaharsha/elevenlabs-tts/SKILL.md) - ElevenLabs TTS——OpenClaw 的高质量 ElevenLabs 集成。
- [elevenlabs-voices](https://github.com/openclaw/skills/tree/main/skills/robbyczgw-cla/elevenlabs-voices/SKILL.md) - 提供 18 种角色、32 种配置的高质量语音合成。
- [eternal-haven-lore-pack](https://github.com/openclaw/skills/tree/main/skills/deepseekoracle/eternal-haven-lore-pack/SKILL.md) - Eternal Haven Chronicles 世界观与神话人格包。
- [faster-whisper](https://github.com/openclaw/skills/tree/main/skills/theplasmak/faster-whisper/SKILL.md) - 使用 faster-whisper 在本地执行语音转文本。
- [feishu-minutes](https://github.com/openclaw/skills/tree/main/skills/autogame-17/feishu-minutes/SKILL.md) - 获取飞书妙记的信息、统计、转录和媒体内容。
- [freshbooks-cli](https://github.com/openclaw/skills/tree/main/skills/haseebuchiha/freshbooks-cli/SKILL.md) - FreshBooks CLI用于管理发票、客户和计费。
- [gettr-transcribe-summarize](https://github.com/openclaw/skills/tree/main/skills/kevin37li/gettr-transcribe-summarize/SKILL.md) - 下载并处理 GETTR 帖子的音频。
- [hebrew-nikud](https://github.com/openclaw/skills/tree/main/skills/shaharsha/hebrew-nikud/SKILL.md) - 面向 AI 代理的希伯来语元音nikud参考工具。
- [her-voice](https://github.com/openclaw/skills/tree/main/skills/matusvojtek/her-voice/SKILL.md) - 让你的代理拥有声音。
- [inworld-tts](https://github.com/openclaw/skills/tree/main/skills/gugic/inworld-tts/SKILL.md) - 通过 Inworld.ai API 将文本转换为语音。
- [jarvis-voice](https://github.com/openclaw/skills/tree/main/skills/globalcaos/jarvis-voice/SKILL.md) - 具备 TTS 与可视化转录风格的金属感 AI 语音人格。
- [kokoro-tts](https://github.com/openclaw/skills/tree/main/skills/edkief/kokoro-tts/SKILL.md) - 使用本地 Kokoro TTS 引擎从文本生成语音音频。
- [lnbits](https://github.com/openclaw/skills/tree/main/skills/talvasconcelos/lnbits/SKILL.md) - 管理 LNbits 闪电钱包(余额、支付、发票)。
- [lnbits-with-qrcode](https://github.com/openclaw/skills/tree/main/skills/jamestsetsekas/lnbits-with-qrcode/SKILL.md) - 管理 LNbits 闪电钱包(余额、支付、发票)。
- [miranda-sag](https://github.com/openclaw/skills/tree/main/skills/jeffpignataro/miranda-sag/SKILL.md) - ElevenLabs 文本转语音,带有 macOS `say` 风格体验。
- [norman-categorize-transactions](https://github.com/openclaw/skills/tree/main/skills/stanlee000/norman-categorize-transactions/SKILL.md) - 审核并分类未归类银行交易,将其与发票匹配并核验账务分录。
- [norman-monthly-reconciliation](https://github.com/openclaw/skills/tree/main/skills/stanlee000/norman-monthly-reconciliation/SKILL.md) - 执行完整月度财务对账:审查交易、匹配发票并检查未结项。
- [ressemble](https://github.com/openclaw/skills/tree/main/skills/adriano-vr/ressemble/SKILL.md) - 使用 Resemble AI HTTP API 实现文本转语音与语音转文本集成。
- [siliconflow-tts-gen](https://github.com/openclaw/skills/tree/main/skills/lilei0311/siliconflow-tts-gen/SKILL.md) - 使用 SiliconFlow APICosyVoice2进行文本转语音。