Skip to content

Speakr is a personal, self-hosted web application designed for transcribing audio recordings

Python

Trim README release-notes history to last two releases; link to GitHub Releases for older versions

Murtaza Nasire39ef3e831a8
diff --git a/README.md b/README.md
index 93a8fc1c..fd4b6c40 100644
--- a/README.md
+++ b/README.md
@@ -260,162 +260,9 @@ No new features, no breaking changes.
- Per-upload / per-tag / per-folder model selection documentation
- `EMBEDDING_BASE_URL` API mode documentation across inquire-mode, vector-store, and troubleshooting
-### Previous Release (v0.8.15-alpha)
-
-**New Transcription Connectors, Upload API Improvements & Bug Fixes**
-
-- **Mistral/Voxtral Connector** - Cloud-based transcription with built-in speaker diarization via Mistral's Voxtral models, with admin-configurable default hotwords
-- **VibeVoice Connector** - Self-hosted transcription via vLLM with speaker diarization, automatic chunking for long files, and no cloud dependency
-- **Upload API: title & meeting_date** - Optional `title` and `meeting_date` fields on the upload API so integrations can set metadata directly
-- **Regenerate Title** - New button to regenerate a recording's title with AI after transcription
-- **Default Transcription Language** - Users can set a default language that auto-fills on upload and reprocess forms
-- **Tag-Driven Auto-Processing** - Watch folders can now auto-apply tags and trigger processing via API
-- **Configurable LLM Timeouts** - Adjust timeout and retry settings for slower local models
-
-**Bug Fixes** - Azure inquire mode crash on empty streaming chunks, chat API returning non-serializable objects, user deletion failing on NOT NULL foreign keys, duration-based chunking ignoring connector limits
-
-### Previous Release (v0.8.14-alpha)
-
-**Fullscreen Video, Custom Vocabulary & Localization**
-
-- **Fullscreen Video Mode** - Double-click or use the expand button to enter a fullscreen video player with auto-hiding controls, live subtitles showing speaker names, and full keyboard shortcuts
-- **Custom Vocabulary (Hotwords)** - Comma-separated words to improve recognition of domain-specific terms, configurable per user, per tag, or per folder
-- **Initial Prompt** - Provide context to steer the transcription model's style and vocabulary
-- **Video Passthrough** - New `VIDEO_PASSTHROUGH_ASR=true` option sends raw video files directly to ASR backends that support video input, skipping audio extraction
-- **Upload Disclaimer Modal** - Configurable disclaimer shown before uploads, with custom banner text in admin settings
-- **Complete Localization** - All recent feature strings (incognito mode, hotwords, upload disclaimer, fullscreen video, groups, SSO, color schemes) now fully localized across all six languages
-
-**Bug Fixes** - Upload notification ordering, speaker snippet extraction for video files with AAC audio, chat textarea staying focused during AI responses, upload queue blocking when adding files while processing, duplicate detection hashing before conversion, markdown list formatting
-
-### Previous Release (v0.8.13-alpha)
-
-**Video Retention Fix** - Fixed large video files silently losing their video stream during upload when `VIDEO_RETENTION=true`. Probe timeout now scales with file size and falls back to extension detection if probing fails.
-
-### Previous Release (v0.8.8)
-
-**Lightweight Docker Image**
-
-- **Lite Image** - New `learnedmachine/speakr:lite` tag (~725MB vs ~4.4GB) skips PyTorch/sentence-transformers for users who don't need semantic search
-- **Multi-Stage Dockerfile** - Optimized build with static ffmpeg binaries and smaller final image for both variants
-- **Improved Text Search** - Better fallback search with stop word filtering, keyword-focused query enrichment, and match ranking
-
-*Thanks to [sakowicz](https://github.com/sakowicz) for the suggestion*
-
-### Previous Release (v0.8.7)
-
-**Export Templates & Localization**
-
-- **Customizable Export Templates** - Create markdown templates for exports with variables (`{{title}}`, `{{summary}}`, `{{notes}}`) and conditionals for optional sections
-- **Localized Labels** - Use `{{label.metadata}}`, `{{label.summary}}` etc. for automatically translated labels based on user's UI language
-- **Localized Date Formatting** - Export dates formatted per user's language preference (e.g., "15. Januar 2026" for German)
-
-**Improvements** - Opt-in ASR chunking, speaker ID remapping across chunks, simplified About page transcription display
-
-**Bug Fixes** - ASR empty text validation, cascade delete for recording relationships, missing model imports
-
-### Previous Release (v0.8.6)
-
-**Folders & Automation**
-
-- **Folders Organization** - Organize recordings into folders with custom prompts and ASR settings per folder
-- **Auto Speaker Labeling** - Automatic speaker identification using voice embedding matching
-- **Per-User Auto-Summarization** - User-configurable automatic summary generation
-- **Azure OpenAI Connector** - New transcription connector for Azure OpenAI (experimental, community testing welcome)
-- **HTTPS Validation** - Clear error messages when attempting to record on non-HTTPS connections
-
-**Improvements** - Legacy ASR code removed (fully migrated to connector architecture), audio codec fallback to MP3, share page click-to-seek, new `READABLE_PUBLIC_LINKS` option for server-rendered transcripts (LLM/scraper accessible)
-
-**Bug Fixes** - PostgreSQL boolean defaults in migrations, folders feature detection, audio player visibility for incognito recordings
-
-### Previous Release (v0.8.5.1)
-
-**Incognito Mode Enhancements & Compatibility Fixes**
-
-- **Incognito Mode for In-App Recordings** - The incognito toggle now works for microphone recordings, not just uploads
-- **Default Incognito Mode** - New `INCOGNITO_MODE_DEFAULT=true` option to start with incognito enabled by default
-- **LLM Streaming Compatibility** - New `ENABLE_STREAM_OPTIONS=false` option for LLM servers that don't support OpenAI's stream_options parameter
-
-### Previous Release (v0.8.5)
-
-**Bulk Operations & Privacy Features**
-
-- **Multi-Select Mode** - Select multiple recordings in sidebar for batch operations (delete, tag, reprocess, toggle inbox/highlight)
-- **Incognito Mode** - Session-only transcription processing with no database storage (enable with `ENABLE_INCOGNITO_MODE=true`)
-- **Playback Speed Control** - Adjustable 0.5x to 3x speed on all audio players with persistent preference
-
-### Previous Release (v0.8.4)
-
-**Bug Fixes** - Fixed language selection not being passed to ASR service, improved reprocess modal
-
-### Previous Release (v0.8.3)
-
-**Naming Templates**
-
-- **Custom Title Formatting** - Create templates with variables like `{{ai_title}}`, `{{filename}}`, `{{date}}` and custom regex patterns
-- **Tag-Based or User Default** - Assign templates to tags or set a user-wide default
-- **Token Savings** - Templates without `{{ai_title}}` skip the AI call entirely
-- **API v1 Upload** - New `/api/v1/upload` endpoint for programmatic recording uploads
-
-**Improvements** - Tag drag-and-drop reordering, registration domain restriction, event delete button, WebM seeking fix
-
-### Previous Release (v0.8.2)
-
-**Transcription Usage Tracking**
-
-- **Per-User Budgets** - Set monthly transcription limits (in minutes) with 80% warning and 100% blocking
-- **Usage Dashboard** - Track minutes, costs, and per-user breakdowns in Admin panel
-- **Cost Estimation** - Automatic pricing for OpenAI Whisper/Transcribe and self-hosted ASR
-
-### Previous Release (v0.8.1)
-
-**Bug Fixes**
-
-- **Diarization for Long Files** - Fixed speaker diarization for chunked files with OpenAI's `gpt-4o-transcribe-diarize`
-- **Empty Segment Filtering** - Removed empty transcript segments from diarized output
-
-### Previous Release (v0.8.0)
-
-**Cloud Diarization & REST API**
-
-- **Speaker Diarization Without GPU** - Use OpenAI's `gpt-4o-transcribe-diarize` for speaker identification with just an API key
-- **REST API v1** - Full-featured API for automation tools (n8n, Zapier, Make) and dashboard widgets
-- **Connector Architecture** - Modular transcription providers with simplified configuration
-- **Virtual Scrolling** - Performance optimization for handling 4500+ transcript segments smoothly
-- **Audio Player Improvements** - Drag-to-seek, independent modal players, improved theme support
-- **File Date Handling** - Uses original recording date from file metadata instead of upload time
-- **Codec Configuration** - Configure unsupported audio codecs with automatic conversion
-
-### Previous Release (v0.7.1)
-
-- **PostgreSQL Support** - Added `psycopg2-binary` driver for PostgreSQL database option
-- **Audio Download Button** - Explicit download button next to audio player, works on mobile
-- **Job Queue Race Condition Fix** - Fixed issue where multiple workers could claim the same job
-
-*Thanks to [sakowicz](https://github.com/sakowicz), [JadedBlueEyes](https://github.com/JadedBlueEyes), and [Daabramov](https://github.com/Daabramov)*
-
-### Previous Release (v0.7.0)
-
-- **SSO Authentication** - Sign in with any OIDC provider (Keycloak, Azure AD, Google, Auth0, Pocket ID)
-- **Account Linking/Unlinking** - Link or unlink SSO from Account settings
-- **Enforce SSO-only** - Disable password login for regular users
-
-*Contributed by [Dmitry Abramov](https://github.com/Daabramov)* | [SSO Setup Guide](https://murtaza-nasir.github.io/speakr/admin-guide/sso-setup/)
-
-### v0.5.9 - Major Release
-
-> **⚠️ IMPORTANT:** v0.5.9 introduced significant architectural changes. If upgrading from earlier versions, backup your data first and review the [configuration guide](https://murtaza-nasir.github.io/speakr/getting-started/installation#configuration-updates).
+---
-#### Highlights
-- **Complete Internal Sharing System** - Share recordings with users with granular permissions (view/edit/reshare)
-- **Group Management & Collaboration** - Create groups with auto-sharing via group tags and custom retention policies
-- **Speaker Voice Profiles** - AI-powered speaker identification with 256-dimensional voice embeddings
-- **Audio-Transcript Synchronization** - Click-to-jump, auto-highlight, and follow mode for interactive navigation
-- **Auto-Deletion & Retention System** - Flexible retention policies with global and group-level controls
-- **Automated Export** - Auto-export transcriptions to markdown for Obsidian, Logseq, and other note-taking apps
-- **Permission System** - Fine-grained access control throughout the application
-- **Modular Architecture** - Backend refactored into blueprints, frontend composables for maintainability
-- **UI/UX Enhancements** - Compact controls, inline editing, unified toast notifications, improved badges
-- **Enhanced Internationalization** - 29 new tooltip translations across all supported languages
+**Older releases:** see the [GitHub Releases page](https://github.com/murtaza-nasir/speakr/releases) for tagged versions, or the [release history on the docs site](https://murtaza-nasir.github.io/speakr/#latest-updates) for narrative changelog entries going back to earlier v0.x lines.
## Screenshots