Convert text to speech and transcribe audio with speaker diarization.
npx skills add https://github.com/eachlabs/skills --skill eachlabs-voice-audio
Please help me install this Agent Skill. Skill: eachlabs-voice-audio Source: https://github.com/eachlabs/skills/tree/main/skills/eachlabs-voice-audio Command: npx skills add https://github.com/eachlabs/skills --skill eachlabs-voice-audio
This Skill provides a comprehensive suite of tools for voice and audio manipulation, including text-to-speech, speech-to-text, and voice conversion, simplifying complex audio tasks.
Use the eachlabs-voice-audio skill to convert the text 'Hello, world!' into speech using the elevenlabs-text-to-speech model.
High-intent search queries and answers about installing and using this skill.
To transcribe audio with speaker labels, speech-to-text models like Whisper and Wizper process audio files to generate text output that includes speaker diarization and timestamps.
Text-to-speech generation using ElevenLabs converts written text into natural-sounding speech, supporting multiple languages for voiceovers and diverse audio generation needs.
Voice conversion and voice cloning transform or replicate voices using models like RVC and ElevenLabs, allowing you to create a custom AI voice for your brand or project.
An API key is required for authentication to run text-to-speech and voice conversion predictions, integrating directly with the EachLabs API for execution.
Audio utilities within the voice and audio processing suite allow you to merge generated audio tracks with existing video files and perform general audio format conversions.
camillanapolesGenerate images from text prompts via the EachLabs Predictions API.
swyxioTranscribe audio and video files using configurable speech recognition backends.
yethikrishnaGenerate images, videos, and speech from JSON prompts via Bash tools.
QcasaresTranscribe audio to text using ElevenLabs' Scribe v2 API.
