All notable changes and updates to our service
Stay up to date with the latest features, improvements, and fixes
2.11.0
Blog Content Update - Convert MP4 to SRT Guide
Published comprehensive guide on converting MP4 to SRT with Harku, covering best practices, format comparisons, and subtitle editing tips
Published in-depth blog post covering step-by-step MP4 to SRT conversion, including accuracy optimization, timing adjustments, and format selection guidance.
Released both English and Chinese versions of the conversion guide, ensuring accessibility for our global user base.
Enhanced blog post rendering with proper Markdown support, including code blocks, tables, and image galleries for better content presentation.
Optimized blog content with targeted keywords including 'convert MP4 to SRT', 'MP4 to VTT', 'generate subtitles', and 'video to text' for improved search visibility.
Added screenshots and visual guides demonstrating the upload process, export options, and two-line SRT formatting best practices.
2.10.0
Subtitle Generator Landing Page Refresh
Launched the dedicated /tools/subtitle-generator page with improved CTA layout, streamlined sample preview, and unified editor interactions.
Shipped a standalone subtitle generator page with SEO metadata, descriptive workflow overview, and localized copy. Added to sitemap for indexing.
Replaced the old card layout with a two-column deliverables view, highlighting AI summary, action items, and decisions in a cleaner format.
Updated the hero and footer CTAs to include a direct link back to the Speech to Text Converter, keeping navigation consistent across tools.
Moved the Time Shift control into the gear menu and aligned its styling with other toggles for a more professional editor toolbar.
2.9.0
Interview Transcription Tool Launch
Professional interview transcription with automatic speaker identification, Q&A format export, and AI quote extraction
Launched /tools/interview-transcription page with specialized features for journalists, researchers, and HR professionals.
AI automatically identifies and extracts memorable quotes, insights, and key statements from interview transcripts with speaker attribution.
Automatic question-answer formatting with interviewer/interviewee labeling, perfect for articles, research papers, and reports.
Advanced speaker diarization automatically separates interviewer from interviewees with rename capability for clarity.
Specialized export formats including Q&A Markdown, journalist format, and academic citation-ready transcripts.
Toggle to remove 'um', 'uh', 'like', and other verbal fillers for publication-ready interview transcripts in English and Chinese.
2.8.0
Blog Launch & Competitor Comparison Articles
Launched comprehensive blog platform with in-depth Harku vs competitor comparison articles
Introduced new /blog section with modern design, category filtering, and SEO-optimized architecture for content discovery.
Detailed comparison covering features, pricing, accuracy, and use cases to help users choose the right transcription tool.
Migrated from /posts to /blog with 301 redirects to maintain SEO rankings and improve URL clarity.
Modern card-based design with hover animations, gradient backgrounds, and improved mobile responsiveness.
2.7.0
Podcast Transcription Tool & Timestamp Fixes
Dedicated podcast transcription tool with AI-generated chapters, summaries, and show notes, plus timestamp validation improvements
Launched /tools/podcast-transcription page with specialized features for podcast content creators.
DeepSeek AI automatically analyzes podcast content to generate structured chapters with titles, timestamps, and summaries.
AI automatically identifies insights, quotes, key moments, and actionable advice with accurate timestamps.
Auto-generate professional Show Notes including episode description, chapter list, highlights, resources, and tags.
Fixed Show Notes timestamps exceeding audio duration - now validates all AI-generated timestamps against actual audio length.
All chapter, highlight, and show notes timestamps are extracted from actual transcription segments, ensuring 100% accuracy.
2.6.0
AI Meeting Transcription Tool
Professional meeting transcription with AI-powered minutes and action items
Upload Zoom, Teams, or Google Meet recordings in MP4, M4A, WAV, MP3, MOV, MKV formats with up to 2GB file size support for anonymous users.
Automatic speaker detection and labeling with timestamps for multi-person conversations and meetings.
Structured meeting minutes with agenda, discussion points, decisions, and next steps automatically extracted from transcripts.
AI identifies commitments, assignees, and due dates with context pulled directly from meeting conversations.
Download meeting transcripts and minutes as DOCX, Markdown, or copy to clipboard for sharing in Slack, Notion, or Confluence.
Live progress indicators and ETA during transcription processing to keep users informed.
Encrypted storage at rest, role-based access controls, optional EU data residency, and configurable retention policies.
Anonymous users can process the first 5 minutes of any meeting recording without signup to check quality.
2.5.1
YouTube Tool UX Updates
Smoother anonymous verification and clearer feature messaging
Turnstile verification tokens now persist so anonymous YouTube previews begin automatically after passing the check.
The Open in Editor action shows a loading spinner to prevent duplicate navigation taps.
Clarified that speaker diarization requires the Basic plan in the YouTube transcript tool.
2.5.0
Audio to Text Enhancement
Major improvements to audio transcription capabilities
Improved audio to text conversion with 98.5% accuracy on clear English audio files
Expanded support to 100+ languages in audio transcription
Optimized keyword density for better search engine visibility
Fixed pricing tiers to correctly show Basic ($19) and Pro ($29) plans
2.4.0
UI/UX Overhaul
Complete redesign of the user interface
Completely redesigned dashboard with better navigation and insights
Added system-wide dark mode support with automatic detection
50% faster processing speed for video and audio files
Enhanced mobile responsiveness and touch interactions
2.3.0
Export Formats & API
New export options and API improvements
Export transcripts as formatted Word documents
New RESTful API with improved rate limits and documentation
Process multiple files simultaneously with queue management
Fixed timestamp alignment issues in SRT exports
2.2.0
Speaker Detection
Advanced speaker identification features
Automatically identify and label different speakers in conversations
Visual timeline showing when each speaker talks
Enhanced transcription accuracy for overlapping speech
2.1.0
Performance Update
Major performance improvements and bug fixes
3x faster transcription for files under 30 minutes
Reduced memory usage by 40% during processing
Fixed file upload failures for large files over 1GB
Resolved UTF-8 encoding issues in exported files
2.0.0
Harku Launch
Initial release of our video and audio to text service
Convert any video format to accurate text transcripts
Support for MP4, MOV, AVI, WebM and 40+ video formats
5-minute free preview for all uploads
Export as TXT, SRT, VTT, JSON, and more
Stay Updated
Subscribe to our newsletter to be the first to know about new features and updates