ScribeForge

Changelog

Stay up to date with the latest improvements and new features

v3.1.0 Latest
April 03, 2026
  • Speed-optimized
  • fixed The Issues of hanging on to low-end cpus
  • Voice Clone Pro Enhanced
v3.0.0
March 31, 2026
  • Voice Clone Pro Added
  • Enterprise-grade voice cloning with just 5–10 seconds of reference audio
  • No base voice selection needed — upload reference audio, type your text, and generate
  • Temperature control slider to fine-tune voice variation and naturalness
  • Pause markers — insert natural pauses directly in your text:
  • Weak (0.15s), Clause (0.3s), Sentence (0.6s), Paragraph (1.0s), or custom durations
  • Say-As markup — control how text is pronounced:
  • Cardinal, ordinal, digits, characters, dates, times, phone numbers, units, and fractions
  • Pre-load engine button so your first generation is instant
  • Real-time progress bar during model loading and generation
  • Free users get 2,000 characters/day to try it out
  • Built-in REST API to control MusaTTS from any app, script, or workflow
  • Endpoints: health check, list voices, TTS synthesis, voice blending, and Voice Clone Pro
  • API key authentication with one-click generation and regeneration
  • Configurable port (1024–65535)
  • Interactive documentation with ready-to-copy examples for Python, cURL, and JavaScript
  • Start/stop the server anytime from the new API Settings page
  • New Voice Clone Pro page with drag-and-drop reference audio upload and audio preview
  • New API Settings page with enable/disable toggle, key management, and live server status
  • Engine status indicator shows whether the Voice Clone Pro model is loaded and ready
v2.0.0
March 18, 2026
  • Clone any voice by uploading a short audio sample of the speaker
  • Type your text, pick a base voice, and generate speech that sounds like the uploaded voice
  • Filter voices by language for quick selection
  • Preview your reference audio before generating
  • Adjust speech speed with a simple slider
  • Audio plays automatically after generation
  • Save your cloned audio as a WAV file
  • Audio-to-Audio Clone
  • Transform any audio file to sound like a different speaker
  • Upload your source audio and a reference voice — MusaTTS handles the rest
  • Supports WAV, MP3, FLAC, OGG, and M4A files
  • Preview both files before cloning
  • See real-time progress while your audio is being converted
  • Free & Pro Plans
  • Free users get 1,000 characters per voice clone, up to 3,000 characters per day
  • Free users get 1 audio-to-audio clone per day
  • Pro users get 5,000 characters per voice clone (adjustable up to 20,000)
  • Pro users get 10,000 characters per TTS generation (adjustable up to 50,000)
  • Pro users get unlimited daily voice clones and audio clones
  • Change your per-generation limit anytime from the settings on each page
  • Improved Upgrade Prompts
  • When you hit a limit, a clear dialog shows exactly what you've used across TTS, Voice Clone, and Audio Clone
  • One-click upgrade button takes you straight to the license page
  • Fixed an issue where deactivating a license could leave the app stuck in Pro mode
v1.0.0
March 08, 2026
  • Fix Issue Of Index Out of bound