Speakr

Docker 应用程序 from learnedmachine's Repository

概述

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.

要求

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.

运行时参数

网络用户界面: http://[IP]:[PORT:8899]
网络: bridge
外壳: sh
特权: false

模板配置

WebUI PortPorttcp

Web interface port

目标: 8899
默认值: 8899
价值: 8899

Uploads VolumePathrw

Storage for uploaded audio files

目标: /data/uploads
默认值: /mnt/user/appdata/speakr/uploads
价值: /mnt/user/appdata/speakr/uploads

Database VolumePathrw

Database and application state

目标: /data/instance
默认值: /mnt/user/appdata/speakr/instance
价值: /mnt/user/appdata/speakr/instance

Exports VolumePathrw

Exported transcriptions (for Obsidian, etc.)

目标: /data/exports
默认值: /mnt/user/appdata/speakr/exports
价值: /mnt/user/appdata/speakr/exports

Auto-Process VolumePathrw

Watch directory for automatic file processing

目标: /data/auto-process
默认值: /mnt/user/appdata/speakr/auto-process
价值: /mnt/user/appdata/speakr/auto-process

Text Model API KeyVariable

API key for OpenRouter or OpenAI (required for summaries)

目标: TEXT_MODEL_API_KEY

Text Model Base URLVariable

API endpoint for text generation

目标: TEXT_MODEL_BASE_URL
默认值: https://openrouter.ai/api/v1
价值: https://openrouter.ai/api/v1

Text Model NameVariable

Model name for text generation

目标: TEXT_MODEL_NAME
默认值: openai/gpt-4o-mini
价值: openai/gpt-4o-mini

Transcription API KeyVariable

OpenAI API key for Whisper transcription (required)

目标: TRANSCRIPTION_API_KEY

Transcription Base URLVariable

Whisper API endpoint

目标: TRANSCRIPTION_BASE_URL
默认值: https://api.openai.com/v1
价值: https://api.openai.com/v1

Whisper ModelVariable

Whisper model to use

目标: WHISPER_MODEL
默认值: whisper-1
价值: whisper-1

Admin UsernameVariable

Initial admin username

目标: ADMIN_USERNAME
默认值: admin
价值: admin

Admin EmailVariable

Initial admin email

目标: ADMIN_EMAIL
默认值: admin@example.com
价值: admin@example.com

Admin PasswordVariable

Initial admin password (CHANGE THIS!)

目标: ADMIN_PASSWORD

Allow RegistrationVariable

Allow new user registration (true/false)

目标: ALLOW_REGISTRATION
默认值: false
价值: false

TimezoneVariable

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

目标: TIMEZONE
默认值: UTC
价值: UTC

Log LevelVariable

Logging level: DEBUG, INFO, WARNING, ERROR

目标: LOG_LEVEL
默认值: INFO
价值: INFO

Summary Max TokensVariable

Maximum tokens for AI summaries

目标: SUMMARY_MAX_TOKENS
默认值: 8000
价值: 8000

Chat Max TokensVariable

Maximum tokens for chat responses

目标: CHAT_MAX_TOKENS
默认值: 5000
价值: 5000

Enable ChunkingVariable

Split large files for API limits (true/false)

目标: ENABLE_CHUNKING
默认值: true
价值: true

Chunk LimitVariable

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

目标: CHUNK_LIMIT
默认值: 20MB
价值: 20MB

Chunk Overlap SecondsVariable

Overlap between chunks in seconds

目标: CHUNK_OVERLAP_SECONDS
默认值: 3
价值: 3

Enable Inquire ModeVariable

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

目标: ENABLE_INQUIRE_MODE
默认值: false
价值: false

Enable Auto ProcessingVariable

Watch directory for automatic file processing (true/false)

目标: ENABLE_AUTO_PROCESSING
默认值: false
价值: false

Auto Process ModeVariable

Processing mode: admin_only, user_directories, or single_user

目标: AUTO_PROCESS_MODE
默认值: admin_only
价值: admin_only

Auto Process Check IntervalVariable

Check interval for new files (seconds)

目标: AUTO_PROCESS_CHECK_INTERVAL
默认值: 30
价值: 30

Enable Auto ExportVariable

Automatically export transcriptions to markdown (true/false)

目标: ENABLE_AUTO_EXPORT
默认值: false
价值: false

Auto Export TranscriptionVariable

Include transcription in exports (true/false)

目标: AUTO_EXPORT_TRANSCRIPTION
默认值: true
价值: true

Auto Export SummaryVariable

Include summary in exports (true/false)

目标: AUTO_EXPORT_SUMMARY
默认值: true
价值: true

Enable Auto DeletionVariable

Enable automatic deletion of old recordings (true/false)

目标: ENABLE_AUTO_DELETION
默认值: false
价值: false

Global Retention DaysVariable

Days to retain recordings (0 = disabled)

目标: GLOBAL_RETENTION_DAYS
默认值: 90
价值: 90

Deletion ModeVariable

Deletion mode: audio_only or full_recording

目标: DELETION_MODE
默认值: audio_only
价值: audio_only

Users Can DeleteVariable

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

目标: USERS_CAN_DELETE
默认值: true
价值: true

Enable Internal SharingVariable

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

目标: ENABLE_INTERNAL_SHARING
默认值: false
价值: false

Show Usernames in UIVariable

Display usernames in interface (true/false)

目标: SHOW_USERNAMES_IN_UI
默认值: false
价值: false

Enable Public SharingVariable

Allow public share links (true/false)

目标: ENABLE_PUBLIC_SHARING
默认值: true
价值: true

Database URIVariable

Database connection string

目标: SQLALCHEMY_DATABASE_URI
默认值: sqlite:////data/instance/transcriptions.db
价值: sqlite:////data/instance/transcriptions.db

类别

Media App > Other Productivity Tools > Utilities

下载统计数据

106,388

下载总数

13,374

本月

13,098

平均每月

长期下载总量

加载图表...

链接

模板支持 Docker Hub Pro连接

详细信息

存储库

learnedmachine/speakr

登记处

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

最后更新2026-03-19

初见2025-12-03

在Unraid 上运行 Speakr 。

Speakr 已被列入Unraid OS 的社区应用程序。探索Unraid ，构建灵活的家庭服务器、NAS 或家庭实验室。

探索Unraid OS