Implements comprehensive audio processing and text-to-speech generation using the Google Gemini API.
The Gemini Audio skill empowers Claude with advanced audio capabilities, enabling it to transcribe, summarize, and analyze audio files up to 9.5 hours in length. It supports a wide range of formats and can distinguish between speech, music, and ambient sounds, while also providing high-quality text-to-speech generation with controllable voice styles. This tool is essential for developers building applications that require deep audio understanding, meeting transcription, or natural-sounding voice responses via Google AI Studio or Vertex AI.
주요 기능
01Seamless integration with both Google AI Studio and Vertex AI endpoints
02High-fidelity transcription with timestamps and multi-speaker identification
03Support for multiple formats including MP3, WAV, FLAC, and AAC
040 GitHub stars
05Long-form audio analysis supporting up to 9.5 hours per request
06Controllable Text-to-Speech (TTS) with adjustable style, pace, and tone
사용 사례
01Automating meeting and podcast transcriptions with speaker detection
02Generating natural-sounding narration or voiceovers for applications
03Extracting insights and summaries from long-form audio recordings
