Speakr

Docker app from learnedmachine's Repository

Overview

Speakr is a self-hosted AI transcription and intelligent note-taking platform. Transform your audio recordings into organized, searchable, and intelligent notes with speaker identification, AI chat, semantic search, and collaboration features.

Key Features:

AI-powered transcription with speaker identification
Voice profiles for automatic speaker recognition
Interactive chat with your recordings
Semantic search across all recordings (Inquire Mode)
Internal sharing and group collaboration
Smart tagging with custom AI prompts
Auto-deletion and retention policies
Automated export to Obsidian/Logseq
Full internationalization (EN, ES, FR, DE, ZH)
Light/dark themes with customizable colors

IMPORTANT: Requires API keys for OpenAI/OpenRouter or local AI services for transcription and text generation.

Requirements

Before starting, you MUST configure API keys:
1. Create a .env file or use environment variables
2. Set TEXT_MODEL_API_KEY (OpenRouter or OpenAI)
3. Set TRANSCRIPTION_API_KEY (OpenAI Whisper)
4. Set ADMIN_USERNAME and ADMIN_PASSWORD

See the GitHub documentation for complete setup instructions.

Runtime arguments

Web UI: http://[IP]:[PORT:8899]
Network: bridge
Shell: sh
Privileged: false

Template configuration

WebUI PortPorttcp

Web interface port

Target: 8899
Default: 8899
Value: 8899

Uploads VolumePathrw

Storage for uploaded audio files

Target: /data/uploads
Default: /mnt/user/appdata/speakr/uploads
Value: /mnt/user/appdata/speakr/uploads

Database VolumePathrw

Database and application state

Target: /data/instance
Default: /mnt/user/appdata/speakr/instance
Value: /mnt/user/appdata/speakr/instance

Exports VolumePathrw

Exported transcriptions (for Obsidian, etc.)

Target: /data/exports
Default: /mnt/user/appdata/speakr/exports
Value: /mnt/user/appdata/speakr/exports

Auto-Process VolumePathrw

Watch directory for automatic file processing

Target: /data/auto-process
Default: /mnt/user/appdata/speakr/auto-process
Value: /mnt/user/appdata/speakr/auto-process

Text Model API KeyVariable

API key for OpenRouter or OpenAI (required for summaries)

Target: TEXT_MODEL_API_KEY

Text Model Base URLVariable

API endpoint for text generation

Target: TEXT_MODEL_BASE_URL
Default: https://openrouter.ai/api/v1
Value: https://openrouter.ai/api/v1

Text Model NameVariable

Model name for text generation

Target: TEXT_MODEL_NAME
Default: openai/gpt-4o-mini
Value: openai/gpt-4o-mini

Transcription API KeyVariable

OpenAI API key for Whisper transcription (required)

Target: TRANSCRIPTION_API_KEY

Transcription Base URLVariable

Whisper API endpoint

Target: TRANSCRIPTION_BASE_URL
Default: https://api.openai.com/v1
Value: https://api.openai.com/v1

Whisper ModelVariable

Whisper model to use

Target: WHISPER_MODEL
Default: whisper-1
Value: whisper-1

Admin UsernameVariable

Initial admin username

Target: ADMIN_USERNAME
Default: admin
Value: admin

Admin EmailVariable

Initial admin email

Target: ADMIN_EMAIL
Default: admin@example.com
Value: admin@example.com

Admin PasswordVariable

Initial admin password (CHANGE THIS!)

Target: ADMIN_PASSWORD

Allow RegistrationVariable

Allow new user registration (true/false)

Target: ALLOW_REGISTRATION
Default: false
Value: false

TimezoneVariable

Timezone for date/time display (e.g., America/New_York)

Target: TIMEZONE
Default: UTC
Value: UTC

Log LevelVariable

Logging level: DEBUG, INFO, WARNING, ERROR

Target: LOG_LEVEL
Default: INFO
Value: INFO

Summary Max TokensVariable

Maximum tokens for AI summaries

Target: SUMMARY_MAX_TOKENS
Default: 8000
Value: 8000

Chat Max TokensVariable

Maximum tokens for chat responses

Target: CHAT_MAX_TOKENS
Default: 5000
Value: 5000

Enable ChunkingVariable

Split large files for API limits (true/false)

Target: ENABLE_CHUNKING
Default: true
Value: true

Chunk LimitVariable

Chunk size limit (e.g., 20MB or 1200s)

Target: CHUNK_LIMIT
Default: 20MB
Value: 20MB

Chunk Overlap SecondsVariable

Overlap between chunks in seconds

Target: CHUNK_OVERLAP_SECONDS
Default: 3
Value: 3

Enable Inquire ModeVariable

Enable AI-powered semantic search across recordings (true/false)

Target: ENABLE_INQUIRE_MODE
Default: false
Value: false

Enable Auto ProcessingVariable

Watch directory for automatic file processing (true/false)

Target: ENABLE_AUTO_PROCESSING
Default: false
Value: false

Auto Process ModeVariable

Processing mode: admin_only, user_directories, or single_user

Target: AUTO_PROCESS_MODE
Default: admin_only
Value: admin_only

Auto Process Check IntervalVariable

Check interval for new files (seconds)

Target: AUTO_PROCESS_CHECK_INTERVAL
Default: 30
Value: 30

Enable Auto ExportVariable

Automatically export transcriptions to markdown (true/false)

Target: ENABLE_AUTO_EXPORT
Default: false
Value: false

Auto Export TranscriptionVariable

Include transcription in exports (true/false)

Target: AUTO_EXPORT_TRANSCRIPTION
Default: true
Value: true

Auto Export SummaryVariable

Include summary in exports (true/false)

Target: AUTO_EXPORT_SUMMARY
Default: true
Value: true

Enable Auto DeletionVariable

Enable automatic deletion of old recordings (true/false)

Target: ENABLE_AUTO_DELETION
Default: false
Value: false

Global Retention DaysVariable

Days to retain recordings (0 = disabled)

Target: GLOBAL_RETENTION_DAYS
Default: 90
Value: 90

Deletion ModeVariable

Deletion mode: audio_only or full_recording

Target: DELETION_MODE
Default: audio_only
Value: audio_only

Users Can DeleteVariable

Allow users to delete their own recordings (true/false)

Target: USERS_CAN_DELETE
Default: true
Value: true

Enable Internal SharingVariable

Enable user-to-user sharing (true/false)

Target: ENABLE_INTERNAL_SHARING
Default: false
Value: false

Show Usernames in UIVariable

Display usernames in interface (true/false)

Target: SHOW_USERNAMES_IN_UI
Default: false
Value: false

Enable Public SharingVariable

Allow public share links (true/false)

Target: ENABLE_PUBLIC_SHARING
Default: true
Value: true

Database URIVariable

Database connection string

Target: SQLALCHEMY_DATABASE_URI
Default: sqlite:////data/instance/transcriptions.db
Value: sqlite:////data/instance/transcriptions.db

Links

Template Support Docker Hub Project

Details

Repository

learnedmachine/speakr

Registry

https://hub.docker.com/r/learnedmachine/speakr

Last Updated2026-03-19

First Seen2025-12-03

Run Speakr on Unraid.

Speakr is listed in Community Apps for Unraid OS. Explore Unraid to build a flexible home server, NAS, or homelab.

Explore Unraid OS