Andrew Babo

No public Store description is available yet.

ffmpeg / ffprobe / yt-dlp / aria2c as a service: probe metadata, extract 16 kHz mono WAV, build 480p proxies, rough cuts, and YouTube downloads. Chainable through key-value store refs.

Face detection + tracking (SCRFD ONNX), torch-free active-speaker detection (mouth motion x audio envelope) and auto-reframe: returns normalized 9:16 crop keyframes ready for an editplan.

Render videos with FFmpeg on Apify: concat storyboards, Ken Burns from stills, or a full editplan (cut, reframe keyframes, layouts, audio mix, captions). Outputs MP4 to a signed URL or the run's key-value store.

Verify email lists at scale. Get honest valid/invalid verdicts for Gmail, Google Workspace, Microsoft 365, Outlook and business domains. No fake accuracy.

No public Store description is available yet.

Scrape Google Maps business data at scale: names, addresses, phones, websites, emails, opening hours, ratings and reviews. HTTP-first engine, 10-30x faster than browser scrapers, breaks the 120-result limit. Export to CSV, Excel, JSON.

Vietnamese text to speech at studio quality: 23 built-in voices (North, Central, South accents, male and female), voice cloning from a 3-8 second clip, English-Vietnamese mixed text and emotion cues. MP3, WAV and Opus output. No rental fee - you pay Apify compute only.

Word-level speech-to-text with whisper.cpp. Accepts any audio or video (https URL or kv ref) and returns a word-level transcript JSON ready for clipping and subtitle pipelines.

Speaker diarization with sherpa-onnx: returns speaker turns and can label an existing word-level transcript with speaker IDs.

Instant AI text-to-speech powered by Qwen3-TTS: 49 natural voices across Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish and Italian. One call returns a ready-to-download WAV/MP3. No GPU or model hosting needed.

Turn text into natural speech in 10 languages, steer delivery with a plain-language style note, or clone a voice from a short clip. Preset speakers, speed control, MP3/WAV/Opus output. No rental fee - you pay Apify compute only.

FFmpeg render engine dành riêng cho CremyX Drama v2: ghép beat (video/ảnh + voice + BGM) thành MP4 rồi upload lên signed URL hoặc key-value store.

The fastest, cheapest way to turn text into speech at scale, with Vietnamese and English voices. Renders many times faster than real time, supports long text and exports MP3, WAV or Opus. No rental fee - you pay Apify compute only.

Bulk image metadata remover. Remove EXIF, GPS, IPTC, XMP, ICC, Stable Diffusion prompt chunks, C2PA Content Credentials and the AI-generated label from photos. Lossless by default, optional pixel scrub against classic invisible watermarks.

Clone a voice from one short English recording and make it read any script with natural expression, including laughs and sighs. Built-in default voice, long text support, MP3/WAV/Opus output. No rental fee - you pay Apify compute only.

Convert text into natural speech with 21 AI voices across English, Spanish, French, Italian, Portuguese, Hindi, Japanese and Chinese. Speed control, long text support, MP3/WAV/Opus download. No rental fee - you pay Apify compute only.

Turn text into speech with built-in voices, or clone a voice from a short recording and have it read anything. English, French, German, Italian, Spanish and Portuguese. MP3, WAV and Opus output. No rental fee - you pay Apify compute only.

Qwen3-4B-Instruct-2507 running on CPU via llama.cpp. Chat completions, system prompts, JSON mode, Q4/Q8 quantization and warm Standby mode.