eachlabs-voice-audioText-to-speech, speech-to-text, voice conversion, and audio processing using EachLabs AI models. Supports ElevenLabs TTS, Whisper transcription with diarization, and RVC voice conversion. Use when the user needs TTS, transcription, or voice conversion.
Install via ClawdBot CLI:
clawdbot install eftalyurtseven/eachlabs-voice-audioGrade 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.eachlabs.ai/v1/prediction`Calls external URL not in known-safe list
https://eachlabs.aiUses known external API (expected, informational)
googleapis.comAI Analysis
The skill's external API calls (api.eachlabs.ai) are consistent with its stated purpose of audio processing and are documented in the skill definition. While it sends user data to an external service, this is expected for the functionality and not unauthorized exfiltration. No hidden instructions, credential harvesting, or obfuscation were found.
Generated Mar 1, 2026
Use TTS models like ElevenLabs to generate high-quality voiceovers for podcast episodes from written scripts, and apply audio trimming utilities for editing. This streamlines content creation for solo creators or small teams.
Leverage Whisper Diarization to transcribe business meetings with speaker identification, enabling automated note-taking and insights extraction for improved collaboration and record-keeping.
Employ ElevenLabs TTS and dubbing models to create multilingual voiceovers for educational videos, making content accessible to diverse audiences and enhancing engagement in online courses.
Utilize voice cloning and conversion models like RVC v2 to generate personalized voice responses in chatbots or IVR systems, providing a consistent and branded customer experience.
Apply audio utilities such as FFmpeg merge to sync high-quality TTS audio with video content, and use sound effects generation for post-production in marketing or film projects.
Offer a cloud-based platform where users pay monthly for access to TTS, transcription, and voice conversion APIs, targeting developers and businesses needing scalable audio solutions.
Provide branded audio processing services to other companies, such as call centers or e-learning platforms, integrating the skill's models into their existing products for a licensing fee.
Offer basic TTS and transcription features for free to attract individual users, with premium upgrades for advanced models like voice cloning or high-volume usage, driving conversions through value-added services.
💬 Integration Tip
Always validate model schemas via the API before predictions to ensure correct inputs and reduce errors in production workflows.
Scored Apr 19, 2026
Audited Apr 16, 2026 · audit v1.0
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.
Start voice calls via the OpenClaw voice-call plugin.
Local text-to-speech via sherpa-onnx (offline, no cloud)