Coming Soon
What we're building next.
🤖 AI Intelligence
Q3 2026Audio Chapters
Auto-detect topic changes and generate named chapter timestamps. YouTube creators spend hours doing this manually.
🧩 Platform
Q4 2026Email & Push Notifications
Get notified when a long transcription job completes. Opt-in email or browser push — for files that take several minutes to process.
Shipped
Everything we've released, newest first.
June 11, 2026
LatestBackground-Safe File Transcription
Upload audio or video, start transcription, and leave the page. Your file can continue processing in the background, and the result will be available from History when it is ready.
Grouped History View
History now has Recent and Grouped views. Grouped view keeps saved summaries, study notes, blog drafts, and other transcript actions together with the original transcript or YouTube video.
PDF to Audio Estimator
Upload a text-based PDF to estimate word count, character count, and listening time before full PDF-to-audio generation goes live. No PDF text is stored and no audio is generated in this preview.
Voice Invoice Generator
Speak or type invoice details, generate an editable invoice, add business details or a logo, and download a professional PDF.
More Smart Tools Inside Dashboard
PDF-to-audio and invoice tools are now available from the dashboard Smart Tools area, so signed-in users can access them from the central workspace.
Cleaner Desktop Navigation
The desktop header now makes Tools, How it works, Developers, and Dashboard easier to discover from the top navigation.
June 6, 2026
FeaturesYouTube Transcripts Now Save to History
Signed-in users can extract a YouTube transcript, save it automatically, and reopen it later from History. Copy the transcript, download it, or continue working from the saved result.
Transcript Results Stay After Sign Up or Login
If you extract a YouTube transcript and then create an account or sign in, your transcript is restored when you return. No more losing the result just because you decided to save your work.
Turn Transcripts Into Useful Outputs
You can now turn YouTube transcripts and uploaded-file transcripts into summaries, key takeaways, study notes, blog drafts, LinkedIn posts, X threads, or your own custom output.
Generated Outputs Are Saved Too
Summaries, notes, drafts, and other generated outputs can now be reopened from History, so your transcript work does not disappear after one session.
Improved History Page
History now makes it easier to reopen saved transcripts, view generated outputs, copy text, download files, and continue from previous work.
Search Across Your Saved Work
Search your saved transcriptions and text-to-speech history by filename, transcript text, or generated content, then reopen the exact item you need.
New Audio to Text Page
Uploaded audio and video transcription now has its own dedicated Audio to Text page, while Speech to Text stays focused on live browser dictation.
Clearer API Usage Dashboard
API usage now separates request count from billable usage and shows real units such as TTS characters and transcription minutes.
Improved Cloud Plan Experience
Cloud plan transcription access, monthly limits, daily upload limits, and file-size limits are now clearer and behave more consistently across the product.
May 15, 2026
DeveloperAPI Keys — Use Voice to Text Online Programmatically
Generate API keys from your dashboard and call VoiceToTextOnline from scripts, automations, and AI agents. Keys use Bearer token auth (v2t_live_...), are SHA-256 hashed and never stored raw, and are shown only once on generation. Free accounts get 2 keys. Full REST API documentation at /developers.
REST API — YouTube Transcript, Text to Speech & Transcribe
Use VoiceToTextOnline from your own apps and automations. The v1 API now supports YouTube transcript extraction, text-to-speech generation, and audio/video transcription with API keys from your dashboard.
MCP Server — Native AI Agent Integration
VoiceToTextOnline now has a Model Context Protocol (MCP) server at /api/mcp. Add one config entry to Claude Desktop, Cursor, or Windsurf and your AI agent can extract YouTube transcripts and generate speech natively — no fetch calls, no glue code. Uses your existing API key and quota. Full setup guide at /mcp.
April 23, 2026
FeaturesTranslate Your Transcript — 30+ Languages
Signed-in users can now translate any transcript into 30+ languages with one click — powered by Google Translate. Click the Translate button in the toolbar, pick your target language, and the translation replaces your text instantly.
AI Enhance Now Available for Registered Users
AI Enhance (clean grammar, format paragraphs, or both) is now a registered-user feature. Guests see a signup prompt when they click it — turning a powerful feature into a growth mechanism.
April 16, 2026
FeaturesFolders — Organise Your Transcripts
After transcribing, save directly to a folder — Podcasts, Interviews, YT Videos, or any name you choose. Create folders from the sidebar with one click. All transcripts are browseable from the new Folders view inside the dashboard.
All Transcripts View Inside Dashboard
Browse, search, and filter all your saved transcripts without leaving the dashboard. Filter by folder, search by content or name, delete — all in one place with the sidebar always visible.
Cloud Sync for Folders
Pro and cloud users get folders and transcripts synced to Supabase automatically. Free registered users get localStorage. All saved transcripts also appear on the public /projects page.
Mobile Dashboard Improvements
Stats cards now display in a 2×2 grid on mobile. Quick action buttons sit side by side. History full-search and folder views stay inside the dashboard on mobile with the bottom nav always visible.
Listed on Capterra
Voice to Text Online is now listed on Capterra — one of the world's largest software review platforms. Find us, leave a review, and help others discover the tool.
March 18, 2026
FeaturesStarter Plan — $7/month
New pricing tier for students and individuals. 200 minutes/month file transcription, 5 files/day, 100MB max file size, speaker diarization included, all export formats (TXT, SRT, VTT, JSON). Annual option at $59/year.
Pay-As-You-Go Credits
Credits now featured on the pricing page. $5 for 100 min, $10 for 240 min, $25 for 650 min, $50 for 1,500 min. Credits never expire. Perfect for students with one-off transcription needs.
Speaker Diarization
Uploaded audio files now automatically detect and label multiple speakers. Speaker A and Speaker B labels appear in the transcript view, all export formats (TXT, SRT, VTT, JSON), and the segments file.
SRT & VTT Export Fixes
Subtitle files now have correct timestamps (previously 240ms was showing as 4:00 — a pre-existing milliseconds conversion bug, now fixed) and sentence-level cue grouping instead of one word per cue.
SEO Architecture Fix
Removed embedded tool component from 98 satellite content pages. Pages are now clean server-rendered content with a CTA linking to the homepage tool — better for Google indexing.
Confidence Heatmap
Transcripts now highlight words by AI confidence level. High confidence words appear normal, uncertain words show a yellow tint (review recommended), and low confidence words show a red tint (verify carefully). Helps journalists, lawyers, and researchers know exactly which parts to double-check.
Structured Data Extraction
One-click AI extraction from any transcript: Meeting Minutes, Action Items, Names Mentioned, Dates & Deadlines, and Summary. Powered by Claude Haiku. Available on dashboard after transcription and in history for past transcripts.
March 17, 2026
SEO55 Language Pages Rewritten
All 55 language-specific voice-to-text pages fully rewritten with unique content, proper CTAs, and no embedded tool component. GSC validation started — pages submitted for re-indexing.
March 2026
FeaturesSmart Voice Tools
Six AI-powered modes for the dictation tool: Meeting Notes, Email Draft, Task Extraction, Invoice, SOAP Notes, Interview Transcript. Each mode formats your dictation appropriately using Claude Haiku.
AI Text Enhancement
One-click AI cleanup after dictation. Three modes: Fix Grammar, Format Paragraphs, or Both. Powered by Claude Haiku.
Text-to-Speech
Convert text to audio with natural-sounding voices. 25+ languages supported. Free tier includes 10,000 characters. Pro and Starter include 500,000 characters/month.
January 2026
FeaturesPro Plan Launched — $15/month
File upload transcription powered by AssemblyAI. Upload MP3, MP4, WAV, M4A files up to 500MB. Get accurate transcripts with word-level timestamps, auto language detection, and export as TXT, SRT, VTT, or JSON.
Save Transcripts Locally
Save and organise voice dictation transcripts in your browser. Folders, tags, search, import/export as JSON. No login required.
55 Languages
Voice-to-text support for 55 languages including Hindi, Arabic, Bengali, Tamil, Vietnamese, Japanese, Korean, and more. Each language has a dedicated page with localised content.
Chrome Extension
Dictate into any text field on any website — Gmail, Google Docs, Notion, Twitter, anywhere you type. Install free from the Chrome Web Store.
October 2025
LaunchVoiceToTextOnline.com Launched
Free browser-based voice-to-text tool. Real-time transcription, 30+ languages, no signup required, no audio stored. Built for privacy-first users.
Try it free
Voice typing is free forever. Upgrade when you need file transcription.
Last updated: June 6, 2026