“audio”

Transcreve, gera voz e trabalha com áudio e música.

Generate audio narration of blog posts using Google Gemini TTS.

When the user wants text-to-speech audio → generate voice files locally (macOS say + afconvert, outputs m4a).

Generate production subtitle artifacts from the final narration audio or final merged video using Volcengine Doubao ASR word timestamps.

Audio forensics and voice recovery guidelines for CSI-level audio analysis.

将视频文件中的音频和视频画面分离。输入一个视频路径，提取出的音频和无声视频会保存到基于 session 生成的特定输出目录下，无声视频会加上 _no_audio 后缀。当用户要求“抽离视频音频”、“提取视频声音”或“分离音视频”时必须调用本技能。

Transcribes audio files and voice notes to text via Gemini 2.5-flash.

Text-guided audio source separation using SAM-Audio via mlx-audio

Extract audio from video files to WAV format.

Converts audio objects stored in Volcengine TOS into PCM-oriented WAV output through TOS data-process async jobs.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

Analyzes a .wav audio file for deepfake risk using acoustic feature extraction

将指定的音频文件混入输入视频的默认播放音轨，并保留视频原有音轨作为非默认备用轨。当用户需要“给视频添加一条音轨”、“把 audio.mp3 merge 到视频里”、“add_audio_track”或“在不替换原音频的情况下加入新音频并默认可听见”时，必须立即调用此技能。

Outils de traitement et de mixage audio.

【音频剪辑工具】支持指定开始时间和结束时间对音频文件进行精确裁剪。当用户需要截取音频片段、去除音频首尾或保留特定时间段时，必须立即调用此技能。

Transcribe a local audio or video file (mp3, m4a, wav, ogg, flac, mp4, mov, webm, ...) to text, fully offline, using faster-whisper.

Use audio-diffusion-pytorch for PyTorch waveform diffusion generators, text-conditioned audio generation, inpainting, upsampling, vocoding, and diffusion…

Transcribe local audio/video and Apple Voice Memos quickly with cached MLX Whisper models, including bad/low-quality audio.

Audio processing utilities - noise reduction, normalization, enhancement

Convert written medical content into podcast or video scripts optimized for audio delivery.

Detect AI-generated deepfake audio used in voice phishing (vishing) by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing…

Generate audio and transcripts for podcast episodes from Fountain screenplays using Produciesta CLI.

将视频文件中的原始音频替换为输入的音频文件。当用户需要“将视频的音频替换为指定音频”、“删除原视频音轨并换成新音频”、“替换视频声音”时，必须立即调用此技能。

Real-time system audio capture and FFT spectrum analysis.