API & MCP Docs

AI Tools

Transcribe speech from audio (wav/mp3/m4a/flac/ogg/webm/aac) to text, SRT, VTT or JSON using the grok-stt AI model. Up to 10 minutes.

AI Tools

AI content-moderation classifier using NSFWJS to flag uploaded images as safe or potentially inappropriate. Built for moderation and compliance review of your own files — it analyzes uploads only and is not an image search or discovery tool. Supports JPEG/PNG/WEBP/GIF.

Text Processing

Run a portable text-cleaning recipe and inspect every step, diff, timing, and character change.

Text Processing

Convert any Unicode text to plain ASCII: strip accents (é→e, ñ→n), romanize Cyrillic/Greek, and transliterate Chinese to pinyin (北京→Bei Jing). Drops emojis and symbols that have no ASCII equivalent.

Text Processing

Encode, decode, visualize, and brute-force the Rail Fence transposition cipher. See the zigzag rail grid and try all rail counts to crack a ciphertext.

Media

Convert synced LRC lyrics into SRT subtitles (each line ends where the next begins, editable last-cue and maximum durations, [offset:] and enhanced word-timing tags handled) and turn SRT subtitles back into LRC lyrics — both directions lossless on text.

Media

Strip hearing-impaired (SDH) noise from subtitles: bracketed sound effects like [APPLAUSE] and (engine rumbles), speaker labels like JOHN: or NARRATOR -, music-note lines ♪ ♫ — then drop the empty cues left behind.

Development

Price a throwaway sandbox across AWS, GCP, Azure, Vercel, Fly.io, Railway, Replit, Codespaces and Gitpod, then audit what forgetting to tear it down actually costs per forgotten day.

Media

Classify a track into genres from measured evidence: GTZAN timbral-texture features, beat-grid pulse shape, band balance, key and dynamics — with a ranked top-3 and the reason behind every pick.