“audio”

Query the Spotify Web API (search tracks/artists/albums, fetch artist, album, playlist, audio features, recommendations) using SPOTIFY_CLIENT_ID /…

Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection.

Transcribe audio or video to text using the on-device ASR model via the zettos-ai engine (private/offline).

Transcribe audio files locally via Whisper CLI or OpenAI Whisper API fallback.

Convert documents and binary files to Markdown with Microsoft MarkItDown (PDF, DOCX, PPTX, XLSX, HTML, images, audio, epub, zip, YouTube URLs).

Collect accessible Bilibili videos, UP uploads, favorites or Watch Later into audio, timestamped transcripts and knowledge-library artifacts using JSON CLI or…

Convert audio/video URLs or local media into corrected Markdown transcripts through Volcengine recording-file ASR 2.0.

Beatoven.ai royalty-free music generation: compose tracks, poll tasks, download audio, fetch individual stems.

Operate ComfyUI-LTXVideo custom nodes for LTX-2 video, audio, IC-LoRA, prompt-conditioning, and advanced ComfyUI workflows.

Use the faster-whisper package for CTranslate2-backed Whisper transcription, model selection, CPU/CUDA setup, audio utilities, VAD, timestamps, and conversion…

Guides FastVideo video, image, and audio generation, config-first inference, serving, training, distillation, evaluation, and performance workflows.

Use when downloading YouTube or Bilibili videos, audio, or subtitles with yt-dlp, especially in the sz-video project.

Save information from a local recording or unsupported audio or video source to BigBrain.

Detect pauses and silence in audio using local dynamic thresholds.

Create a narrated video walkthrough of a pull request with code slides and audio narration.

Translate and dub videos from one language to another, replacing the original audio with TTS while keeping the video intact.

Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site.

Use when the user wants to transcribe a video or audio file to text with word-level timestamps — spins up a self-contained local Whisper (whisper.cpp) Docker…

Outils d'analyse et de découverte audio.

Implement speech-to-text (ASR/automatic speech recognition) capabilities using the z-ai-web-dev-sdk.

Use when the user wants to generate speech, voiceover, or text-to-audio.

Direct interface to the robot's creative visual generation system (TTI) and audio playback via the mixer.

Transcribe audio or video from a local file path or public media URL with Groq, with a read-only dependency preflight that suggests manual installations…

Find YouTube videos and download video or audio from a link into the sandbox's downloads folder.