OpenClaw AI 技能

Alibaba Cloud BAIlian Qwen TTS with voice/mood pre设置s

提供本地高速、高质量文本转语音服务，支持语音克隆与自动路径管理，无需云端确保隐私安全。

Local TTS 路由r for 应用le Silicon — pull 模型s, serve OpenAI-compatible API, synthesize speech, clone voices. Use when the user asks to "生成 speech", "text

Convert short drama dia记录ues into multi-character, emotional TTS audio matching scene rhythm for enhanced expressive content.

Local text-to-speech via sherpa-onnx (offline, no cloud)

MOSI Studio 音频全套能力：语音转文字（ASR）、文字转语音（TTS）、 多说话人对话合成、声音克隆、飞书语音气泡。 两类触发场景： 1. 消息中包含 "[media attached:"、"audio/ogg"、"audio/opus" 或 路径 /home/OpenClaw/.O

Use Zhipu (智谱) 网页 搜索 API for 搜索ing the internet. Use when user asks for 网页 搜索, latest news, or needs current in格式化ion.

Convert text to speech using the To获取herAI API with the MiniMax speech-2.6-turbo 模型 and save audio in mp3 格式化.

Local Vietnamese text-to-speech via VITS2 (offline, no cloud). Supports 5 built-in speaker voices and zero-shot voice cloning from reference audio.

生成 speech from text using KyutAI Pocket TTS - lightweight, CPU-friendly, 流ing TTS with voice cloning. English only. ~6x real-time on M4 MacBook AIr.

MiniMax TTS 文字转语音模型，支持 speech-02/speech-01 系列，生成高质量语音。使用 MINIMAX_API_KEY 环境变量。

百炼 TTS 语音合成，支持多种音色切换，生成高质量中文语音，需配置百炼 API Key。

MiniMax TTS 技能 (enhanced). Multi-代理 voice support (each 代理 can select a unique voice written in SOUL.md), native voice message for Telegram (MP3) and

Text-to-speech (TTS) via ElevenLabs. Use when the user asks to reply with voice/audio, 生成 a spoken version of some text, or asks for “voz”, “nota de v

基于 mlx-audio 的本地文本转语音，支持多语言和多模型，输出音频文件限于指定路径，无需 API 密钥。

Text-to-speech conversion using UniSound's TTS 网页Socket API for generating high-质量 Chinese Mandarin audio from text. Supports multiple voices, adjusta

Convert text to natural speech with DIA TTS, Kokoro, Chatterbox, and more via inference.sh 命令行工具. 模型s: DIA TTS (conversational), Kokoro TTS, Chatterbo

Command-line 工具 for fast, accurate speech-to-text transcription from local files, URLs, or live audio using Deepgram’s API with customizable options.

Transcribe audio and video files to text with speaker 检测ion, timestamps, and 格式化 conversion.

Manage MiniMax Speech 2.8 T2A (text-to-audio) and voice cata记录 lookups. Trigger when you need a precise MiniMax voice_id, a Speech 2.8 TTS 请求, or to 列