speech-notes将录音/语音转写为结构化演讲纪要。适用于:会议讲话、内部分享、演讲录音的转写整理。 触发条件:用户发送音频文件并要求整理/转写/纪要,或要求将已有转写文本整理成结构化纪要。
Install via ClawdBot CLI:
clawdbot install guoqunabc/speech-notesGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 20, 2026
Transcribes executive speeches or team discussions into structured notes for internal distribution. Ensures key decisions and action items are clearly documented without AI artifacts, suitable for companies needing formal records.
Converts recorded academic talks or training sessions into organized summaries. Preserves the speaker's first-person perspective and key insights, aiding students or professionals in review and study materials.
Processes audio from industry conferences or public speeches into polished notes. Highlights core themes and impactful quotes, useful for attendees or organizers to share highlights with stakeholders.
Transcribes media content into structured formats for publication or analysis. Maintains conversational tone while removing filler words, ideal for content creators needing readable summaries.
Converts recorded legal discussions or compliance updates into formal documents. Ensures accuracy and clarity while adhering to structured formatting, supporting regulatory documentation needs.
Offers tiered plans based on usage volume (e.g., hours of audio processed per month). Includes features like priority support and advanced formatting options, targeting businesses with regular transcription needs.
Charges per audio minute processed, with discounts for bulk usage. Appeals to occasional users or small teams, providing flexibility without long-term commitments.
Provides custom integrations with corporate tools like Feishu, along with dedicated support and security compliance. Targets large organizations needing scalable, secure transcription solutions.
💬 Integration Tip
Integrate with Feishu APIs for seamless document creation and updates, ensuring real-time collaboration and formatting consistency.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Local text-to-speech via sherpa-onnx (offline, no cloud)
Start voice calls via the OpenClaw voice-call plugin.