Tag: audio-processing
tool
★ 4,829
Transcribe audio files using OpenAI Whisper API
This tool facilitates audio transcription by interacting with the OpenAI Whisper API endpoint. Developers can submit audio files and optionally specify language or prompts, receiving the output as plain text or structured JSON.
skill
Custom Voice Cloning and Impressions for VoiceMode
This skill enables voice cloning and custom impressions for VoiceMode by synthesizing fresh speech using a local TTS service. It requires a short reference clip and operates via the mlx-audio backend on Apple Silicon.