Andrew Babo

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.

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 on CPU with whisper.cpp. Transcribe video or audio in 90+ languages and get word timestamps, confidence scores and ready-to-use caption segments as JSON.

Analyze any song or video soundtrack and get a precise beat grid: BPM, every beat and bar timestamp, energy curve, drop and breakdown points, section mood labels, plus ready-to-import markers for Premiere, DaVinci, Audacity and CapCut. 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.

No public Store description is available yet.

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