google-voiceGoogle Voice web-client automation and MCP integration from HAR captures. Use when reverse-engineering voice.google.com.har or call_voice.google.com.har, lis...
Install via ClawdBot CLI:
clawdbot install earlvanze/google-voiceGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
Eval(Calls external URL not in known-safe list
https://voice.google.com/u/2/messages?itemId=t.%2B17025038136`Uses known external API (expected, informational)
googleapis.comAI Analysis
The skill primarily automates Google Voice operations via local browser/CDP and HAR captures, with explicit user approval required for sending SMS and placing calls. No evidence of unauthorized data exfiltration, hidden overrides, or credential harvesting; the external URLs are legitimate Google Voice endpoints used as intended.
Generated Oct 25, 2026
A real estate agent receives inbound Google Voice texts from listing inquiries and uses the skill to pull full SMS thread records via itemId URLs, then exports them to JSON for CRM import. Approved replies are sent back through gv_send_sms after confirming recipient and message text.
A service business monitors the logged-in Google Voice web client for missed inquiries and reads thread history to recover context before responding. With explicit approval, the owner initiates outbound calls through the CDP UI automation script and sends confirmation texts to customers.
An operations manager exports received SMS records for their own account to audit response times and conversation history, using the CLI with --format md and --limit. Raw payloads and phone numbers are kept out of shared reports per the privacy guidance.
A clinic or salon uses the optional audio-injection mode to place approved outbound calls that play a TTS reminder message to confirmed numbers. Each number and exact message is explicitly approved before removing --dry-run, and call audio is optionally recorded for verification.
A developer reverse-engineers voice.google.com.har to understand SMS endpoints and builds or debugs an MCP server exposing gv_list_threads and gv_get_thread. They run the HAR analyzer to summarize endpoints without leaking cookies or auth headers.
Consultants package the Google Voice MCP server and CLI scripts as a fixed-scope integration for small businesses needing SMS export, CRM sync, or approved outbound calling. Delivery includes HAR analysis setup, CDP browser configuration, and safety review.
An agency operates the skill on behalf of client accounts, handling approved SMS follow-ups and outbound call campaigns for leads and reminders. Operators maintain the logged-in browser session and enforce explicit-approval workflows for every message and number.
A CRM or practice-management vendor embeds the bundled MCP server as a Google Voice connector feature, letting customers list, read, and export SMS threads and trigger approved calls from within their product.
💬 Integration Tip
Require GV_API_KEY and a live CDP-connected logged-in Google Voice tab (e.g., GV_CDP_URL=http://127.0.0.1:19222), and always gate gv_send_sms and outbound calls behind explicit recipient and message approval.
Scored Oct 25, 2026
Audited May 10, 2026 · audit v1.0
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.