ttsConvert text to speech using Hume AI (or OpenAI) API. Use when the user asks for an audio message, a voice reply, or to hear something "of vive voix".
Install via ClawdBot CLI:
clawdbot install AMSTKO/ttsConvert text to speech and generate audio files (MP3).
9e1f9e4f-691a-4bb0-b87c-e306a4c838efHUME_API_KEY and HUME_SECRET_KEY.HUME_API_KEY="..." HUME_SECRET_KEY="..." node {baseDir}/scripts/generate_hume_speech.js --text "Hello Jonathan" --output "output.mp3"novaOPENAI_API_KEY="..." node {baseDir}/scripts/generate_speech.js --text "..." --output "..."MEDIA: line with the absolute path to the generated file.message tool to send the resulting file to the user.Generated Mar 1, 2026
Automatically generate spoken replies for customer inquiries in call centers or chatbots, providing immediate audio feedback. This reduces wait times and enhances accessibility for visually impaired users.
Convert textbooks, articles, or online learning materials into audio format for students or lifelong learners. This supports auditory learning styles and enables multitasking while listening.
Create personalized voice messages for marketing campaigns, such as promotional announcements or product demos. This adds a human touch to digital communications and can increase engagement rates.
Generate audio versions of written content like news articles or reports for users with visual impairments or reading difficulties. This ensures compliance with accessibility standards and broadens audience reach.
Offer a cloud-based TTS service with tiered pricing based on usage volume or features, such as voice customization or API calls. This provides recurring revenue and scales with customer growth.
Sell access to the TTS API for integration into third-party applications like mobile apps or enterprise software. Charge per request or offer bulk usage packages to developers and businesses.
Provide customizable TTS tools for resale by other companies under their own branding, targeting industries like e-learning or telecommunications. This generates revenue through one-time setup fees and ongoing support.
💬 Integration Tip
Store API keys securely in environment variables and use the provided scripts to generate and send audio files via the message tool for seamless user delivery.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
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.
End-to-end encrypted agent-to-agent private messaging via Moltbook dead drops. Use when agents need to communicate privately, exchange secrets, or coordinate without human visibility.
Text-to-speech via OpenAI Audio Speech API.