Speakr
Aplicación Docker from learnedmachine's Repository
Visión general
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.
Requisitos
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.
Argumentos en tiempo de ejecución
- Interfaz web
http://[IP]:[PORT:8899]- Red
bridge- Concha
sh- Privilegiado
- false
Configuración de plantillas
Web interface port
- Objetivo
- 8899
- Por defecto
- 8899
- Valor
- 8899
Storage for uploaded audio files
- Objetivo
- /data/uploads
- Por defecto
- /mnt/user/appdata/speakr/uploads
- Valor
- /mnt/user/appdata/speakr/uploads
Database and application state
- Objetivo
- /data/instance
- Por defecto
- /mnt/user/appdata/speakr/instance
- Valor
- /mnt/user/appdata/speakr/instance
Exported transcriptions (for Obsidian, etc.)
- Objetivo
- /data/exports
- Por defecto
- /mnt/user/appdata/speakr/exports
- Valor
- /mnt/user/appdata/speakr/exports
Watch directory for automatic file processing
- Objetivo
- /data/auto-process
- Por defecto
- /mnt/user/appdata/speakr/auto-process
- Valor
- /mnt/user/appdata/speakr/auto-process
API key for OpenRouter or OpenAI (required for summaries)
- Objetivo
- TEXT_MODEL_API_KEY
API endpoint for text generation
- Objetivo
- TEXT_MODEL_BASE_URL
- Por defecto
- https://openrouter.ai/api/v1
- Valor
- https://openrouter.ai/api/v1
Model name for text generation
- Objetivo
- TEXT_MODEL_NAME
- Por defecto
- openai/gpt-4o-mini
- Valor
- openai/gpt-4o-mini
OpenAI API key for Whisper transcription (required)
- Objetivo
- TRANSCRIPTION_API_KEY
Whisper API endpoint
- Objetivo
- TRANSCRIPTION_BASE_URL
- Por defecto
- https://api.openai.com/v1
- Valor
- https://api.openai.com/v1
Whisper model to use
- Objetivo
- WHISPER_MODEL
- Por defecto
- whisper-1
- Valor
- whisper-1
Initial admin username
- Objetivo
- ADMIN_USERNAME
- Por defecto
- admin
- Valor
- admin
Initial admin email
- Objetivo
- ADMIN_EMAIL
- Por defecto
- admin@example.com
- Valor
- admin@example.com
Initial admin password (CHANGE THIS!)
- Objetivo
- ADMIN_PASSWORD
Allow new user registration (true/false)
- Objetivo
- ALLOW_REGISTRATION
- Por defecto
- false
- Valor
- false
Timezone for date/time display (e.g., America/New_York)
- Objetivo
- TIMEZONE
- Por defecto
- UTC
- Valor
- UTC
Logging level: DEBUG, INFO, WARNING, ERROR
- Objetivo
- LOG_LEVEL
- Por defecto
- INFO
- Valor
- INFO
Maximum tokens for AI summaries
- Objetivo
- SUMMARY_MAX_TOKENS
- Por defecto
- 8000
- Valor
- 8000
Maximum tokens for chat responses
- Objetivo
- CHAT_MAX_TOKENS
- Por defecto
- 5000
- Valor
- 5000
Split large files for API limits (true/false)
- Objetivo
- ENABLE_CHUNKING
- Por defecto
- true
- Valor
- true
Chunk size limit (e.g., 20MB or 1200s)
- Objetivo
- CHUNK_LIMIT
- Por defecto
- 20MB
- Valor
- 20MB
Overlap between chunks in seconds
- Objetivo
- CHUNK_OVERLAP_SECONDS
- Por defecto
- 3
- Valor
- 3
Enable AI-powered semantic search across recordings (true/false)
- Objetivo
- ENABLE_INQUIRE_MODE
- Por defecto
- false
- Valor
- false
Watch directory for automatic file processing (true/false)
- Objetivo
- ENABLE_AUTO_PROCESSING
- Por defecto
- false
- Valor
- false
Processing mode: admin_only, user_directories, or single_user
- Objetivo
- AUTO_PROCESS_MODE
- Por defecto
- admin_only
- Valor
- admin_only
Check interval for new files (seconds)
- Objetivo
- AUTO_PROCESS_CHECK_INTERVAL
- Por defecto
- 30
- Valor
- 30
Automatically export transcriptions to markdown (true/false)
- Objetivo
- ENABLE_AUTO_EXPORT
- Por defecto
- false
- Valor
- false
Include transcription in exports (true/false)
- Objetivo
- AUTO_EXPORT_TRANSCRIPTION
- Por defecto
- true
- Valor
- true
Include summary in exports (true/false)
- Objetivo
- AUTO_EXPORT_SUMMARY
- Por defecto
- true
- Valor
- true
Enable automatic deletion of old recordings (true/false)
- Objetivo
- ENABLE_AUTO_DELETION
- Por defecto
- false
- Valor
- false
Days to retain recordings (0 = disabled)
- Objetivo
- GLOBAL_RETENTION_DAYS
- Por defecto
- 90
- Valor
- 90
Deletion mode: audio_only or full_recording
- Objetivo
- DELETION_MODE
- Por defecto
- audio_only
- Valor
- audio_only
Allow users to delete their own recordings (true/false)
- Objetivo
- USERS_CAN_DELETE
- Por defecto
- true
- Valor
- true
Enable user-to-user sharing (true/false)
- Objetivo
- ENABLE_INTERNAL_SHARING
- Por defecto
- false
- Valor
- false
Display usernames in interface (true/false)
- Objetivo
- SHOW_USERNAMES_IN_UI
- Por defecto
- false
- Valor
- false
Allow public share links (true/false)
- Objetivo
- ENABLE_PUBLIC_SHARING
- Por defecto
- true
- Valor
- true
Database connection string
- Objetivo
- SQLALCHEMY_DATABASE_URI
- Por defecto
- sqlite:////data/instance/transcriptions.db
- Valor
- sqlite:////data/instance/transcriptions.db
Descargar estadísticas
Descargas totales a lo largo del tiempo
Detalles
learnedmachine/speakrEjecute Speakr en Unraid.
Speakr se encuentra en Community Apps para Unraid OS. Explore Unraid para crear un servidor doméstico flexible, un NAS o un laboratorio doméstico.