“audio”

Manually transcribe a spoken-word audio file with OpenAI gpt-transcribe.

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.

Generates narrated MP3 audio from text or Markdown files by first producing a TTS-friendly intermediate version, then using Kokoro through oMLX in one…

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。

Convert audio files between WAV, OGG, and MP3 with ffmpeg.

Real-time system audio capture and FFT spectrum analysis.

Transcribe local audio or video quickly through Codex Desktop's existing ChatGPT authentication without launching another app instance or replaying media in…

Use when the user wants a fully local offline transcription of a local audio or video file into a clean plain-text transcript saved in the workspace.

将语音转写项目输出的复杂文件结构整理合并为适合 Obsidian 归档的 Markdown 文档

Transcribe local audio to plain text with whisper-cpp; default language is Italian.

Transcribe inbound audio clips to text using local Whisper (faster-whisper).

Synthesize an existing A:/B: VOICEVOX-kana dialogue script into AAC/m4a with local VOICEVOX and ffmpeg.

对大量语音转写稿进行校对、整理、分段处理，支持断点续传和恢复

Транскрибация аудио/видео через Deepgram API: спикеры, таймкоды, форматированный .md

基于字节跳动火山引擎Ark平台的多模态音频理解工具，原生支持音频输入。只要用户提到分析音频内容、理解一段音/视频里的声音、判断说话人音色是否一致、识别 BGM 风格/情绪、判断是否同一个人在说话、做角色音色一致性比对、评估音频是否有断裂/静音/拼接痕迹等需求时，必须优先使用本技能，不要手动抽特征或调本地声纹模型。

Work on the pingis audio collection, review, preprocessing, training, model export, live racket-contact detection, table/floor/noise veto behavior, and…

【人声与背景音分离工具】基于 Demucs (htdemucs) 把一段音频/视频里的人声轨从 BGM/伴奏中分离出来,产出 vocals.wav (干净人声) + bgm.wav (无人声背景)。当用户要求分离人声/伴奏、去 BGM、提取干净人声、做声纹比对前的预处理、或要单独评估 BGM…

Builds SFX and haptics behind ports.

ASR with ~30ms timestamp precision using Qwen3-ASR + ForcedAligner

Turn any topic into a short audio course.