voice-agent-v1Enables autonomous cloning of your voice via ElevenLabs, converts text to speech, and deploys AI voice agents for automated inbound/outbound calls with Twili...
Install via ClawdBot CLI:
clawdbot install georges91560/voice-agent-v1Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://api.elevenlabs.io/v1/voices/addCalls external URL not in known-safe list
https://elevenlabs.ioAudited Apr 18, 2026 · audit v1.0
Generated May 6, 2026
Use the voice agent to automatically call leads from a CRM, deliver a personalized pitch using a cloned voice, handle objections, and book meetings. Ideal for sales teams wanting to scale outreach without hiring more reps.
Deploy the conversational AI agent to answer inbound calls at any hour, qualify leads, answer FAQs, and route complex issues to human agents. Perfect for service businesses that need round-the-clock availability.
Generate MP3 audio for video sales letters (VSLs), podcast episodes, video narrations, and social media clips using the cloned voice, enabling rapid content creation without recording sessions.
Automate personalized voice messages to nurture leads through a sales funnel, such as follow-ups after a webinar or abandoned cart reminders, increasing engagement and conversion rates.
Offer voice agent setup and management as a service to clients, handling voice cloning, call automation, and configuration for a monthly retainer or per-project fee.
Integrate the voice agent into an existing SaaS platform (e.g., CRM, helpdesk) as a premium add-on that enables voice calling and voice content generation.
Use the voice agent to automate outbound calls and qualify leads at scale, then sell those qualified leads to businesses in high-ticket industries like real estate or insurance.
💬 Integration Tip
Ensure the ELEVENLABS_API_KEY and TWILIO credentials are available in config.json or .env, and place voice sample MP3 files in /workspace/voice/samples/ before first run.
Scored May 6, 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.