Speakr is a personal, self-hosted web application designed for transcribing audio recordings
Python
Docs: add v0.9.0 env vars (embeddings, recording sessions, webhooks, token limits, session cookie) to env examples + install guide
Murtaza Nasir7a970c90f395
diff --git a/config/env.asr.example b/config/env.asr.exampleindex 158db342..9c1cb724 100644--- a/config/env.asr.example+++ b/config/env.asr.example@@ -108,6 +108,15 @@ ASR_DIARIZE=true# Common values: 600 (10 min), 1200 (20 min), 1800 (30 min), 3600 (1 hour)# ASR_MAX_DURATION_SECONDS=7200+# --- Transcription Model Dropdown ---+# Comma-separated list of transcription model names offered in the per-upload+# model dropdown. Leave empty to hide the dropdown and always use the+# configured backend. Example: whisper-1,gpt-4o-transcribe-diarize+# TRANSCRIPTION_MODELS_AVAILABLE=++# Enable app-level chunking for the Mistral transcription connector (default: false).+# MISTRAL_ENABLE_CHUNKING=false+# --- Application Settings ---# Set to "true" to allow user registration, "false" to disableALLOW_REGISTRATION=false@@ -116,6 +125,15 @@ ALLOW_REGISTRATION=falseREGISTRATION_ALLOWED_DOMAINS=SUMMARY_MAX_TOKENS=8000CHAT_MAX_TOKENS=5000+# Max tokens for auto title generation (default: 5000)+# TITLE_MAX_TOKENS=5000+# Max tokens for event extraction (default: 3000)+# EVENT_MAX_TOKENS=3000++# --- Session Security ---+# Only send the session cookie over HTTPS. Set to true in HTTPS production+# deployments. Default: false (so plain-HTTP local setups keep working).+# SESSION_COOKIE_SECURE=false# Timezone for displaying dates and times in the UI# Use a valid TZ database name (e.g., "America/New_York", "Europe/London", "UTC")@@ -151,6 +169,20 @@ ADMIN_PASSWORD=changeme# Requires additional dependencies (already included in Docker image)ENABLE_INQUIRE_MODE=false+# Embedding model for Inquire-mode semantic search.+# Default is a local sentence-transformers model (no API needed).+# EMBEDDING_MODEL=all-MiniLM-L6-v2++# To use an OpenAI-compatible embeddings API instead of the local model,+# set the endpoint and API key below. When EMBEDDING_BASE_URL is set,+# Inquire embeddings are generated via the API instead of locally.+# EMBEDDING_BASE_URL=+# EMBEDDING_API_KEY=++# Optional fixed embedding dimensionality. Leave empty to auto-detect from+# the model/endpoint.+# EMBEDDING_DIMENSIONS=+# --- Automated File Processing (Black Hole Directory) ---# Set to "true" to enable automated file processingENABLE_AUTO_PROCESSING=false@@ -244,10 +276,41 @@ INCOGNITO_MODE_DEFAULT=false# Default: false (video uploads extract audio only, video stream is discarded)VIDEO_RETENTION=false+# --- Video Passthrough to ASR ---+# Send original video files directly to ASR without extracting audio.+# Useful for custom ASR backends that handle video internally (e.g., multi-track audio extraction).+# When enabled, video files bypass audio extraction, codec conversion, and chunking.+# Only affects video files — audio uploads are processed normally.+# Default: false+# VIDEO_PASSTHROUGH_ASR=false+# --- Concurrent Uploads ---# Maximum number of simultaneous file uploads (default: 3)MAX_CONCURRENT_UPLOADS=3+# --- Server-Side Recording Sessions (optional) ---+# Opt-in: in-app recordings stream audio chunks to the server as they record,+# instead of buffering the entire recording in browser RAM. This enables+# hours-long recordings and resume-on-reload if the tab is closed or refreshed.+# Default: false (recordings are buffered in the browser).+# ENABLE_SERVER_RECORDING_CHUNKS=false+#+# Absolute ceiling (in hours) on a single in-app recording when server+# chunking is enabled.+# RECORDING_MAX_HOURS=8+#+# Per-user soft storage cap (in bytes) for in-progress server recording+# sessions. Default: 5368709120 (5 GB).+# RECORDING_SESSION_MAX_BYTES_PER_USER=5368709120++# --- Webhooks (optional) ---+# Outbound webhooks notify external services when events occur. Configured+# per-user in the UI.+# Master kill-switch for outbound webhook delivery (default: true).+# WEBHOOK_GLOBAL_ENABLED=true+# Maximum number of webhook subscriptions allowed per user (default: 10).+# WEBHOOK_MAX_PER_USER=10+# --- Background Processing Queues ---# Separate queues for transcription (slow) and summary (fast) jobs# This prevents slow ASR jobs from blocking quick summary generationdiff --git a/config/env.transcription.example b/config/env.transcription.exampleindex 5d91e020..61118125 100644--- a/config/env.transcription.example+++ b/config/env.transcription.example@@ -84,6 +84,11 @@ TRANSCRIPTION_MODEL=gpt-4o-transcribe-diarize# Legacy Whisper model name (used when TRANSCRIPTION_MODEL is not set)# WHISPER_MODEL=whisper-1+# Comma-separated list of transcription model names offered in the per-upload+# model dropdown. Leave empty to hide the dropdown and always use the model+# configured above. Example: whisper-1,gpt-4o-transcribe,gpt-4o-transcribe-diarize+# TRANSCRIPTION_MODELS_AVAILABLE=+# =============================================================================# ASR ENDPOINT CONFIGURATION (For self-hosted whisper services)# =============================================================================@@ -122,6 +127,9 @@ TRANSCRIPTION_MODEL=gpt-4o-transcribe-diarize## To use a custom Mistral-compatible endpoint:# TRANSCRIPTION_BASE_URL=https://api.mistral.ai+#+# Enable app-level chunking for the Mistral connector (default: false).+# MISTRAL_ENABLE_CHUNKING=false# =============================================================================# VIBEVOICE CONFIGURATION (Self-hosted via vLLM)@@ -214,9 +222,18 @@ ALLOW_REGISTRATION=false# Leave empty to allow all domains. Example: company.com,subsidiary.orgREGISTRATION_ALLOWED_DOMAINS=+# --- Session Security ---+# Only send the session cookie over HTTPS. Set to true in HTTPS production+# deployments. Default: false (so plain-HTTP local setups keep working).+# SESSION_COOKIE_SECURE=false+# --- Token Limits ---SUMMARY_MAX_TOKENS=8000CHAT_MAX_TOKENS=5000+# Max tokens for auto title generation (default: 5000)+# TITLE_MAX_TOKENS=5000+# Max tokens for event extraction (default: 3000)+# EVENT_MAX_TOKENS=3000# --- Timezone ---# Use a valid TZ database name (e.g., "America/New_York", "Europe/London", "UTC")@@ -250,6 +267,20 @@ AUDIO_BITRATE=128k# --- Inquire Mode (AI search across all recordings) ---ENABLE_INQUIRE_MODE=false+# Embedding model for Inquire-mode semantic search.+# Default is a local sentence-transformers model (no API needed).+# EMBEDDING_MODEL=all-MiniLM-L6-v2++# To use an OpenAI-compatible embeddings API instead of the local model,+# set the endpoint and API key below. When EMBEDDING_BASE_URL is set,+# Inquire embeddings are generated via the API instead of locally.+# EMBEDDING_BASE_URL=+# EMBEDDING_API_KEY=++# Optional fixed embedding dimensionality. Leave empty to auto-detect from+# the model/endpoint.+# EMBEDDING_DIMENSIONS=+# --- Automated File Processing (Black Hole Directory) ---ENABLE_AUTO_PROCESSING=false# AUTO_PROCESS_MODE=admin_only@@ -296,6 +327,36 @@ VIDEO_RETENTION=false# Maximum number of simultaneous file uploads (default: 3)MAX_CONCURRENT_UPLOADS=3+# =============================================================================+# SERVER-SIDE RECORDING SESSIONS (optional)+# =============================================================================+# Opt-in: in-app recordings stream audio chunks to the server as they record,+# instead of buffering the entire recording in browser RAM. This enables+# hours-long recordings and resume-on-reload if the tab is closed or refreshed.+# Default: false (recordings are buffered in the browser).+# ENABLE_SERVER_RECORDING_CHUNKS=false++# Absolute ceiling (in hours) on a single in-app recording when server+# chunking is enabled.+# RECORDING_MAX_HOURS=8++# Per-user soft storage cap (in bytes) for in-progress server recording+# sessions. Default: 5368709120 (5 GB).+# RECORDING_SESSION_MAX_BYTES_PER_USER=5368709120++# =============================================================================+# WEBHOOKS (optional)+# =============================================================================+# Outbound webhooks notify external services when events occur (e.g. a+# recording finishes processing). Configured per-user in the UI.++# Master kill-switch for outbound webhook delivery. Set to false to disable+# all webhook delivery globally. Default: true.+# WEBHOOK_GLOBAL_ENABLED=true++# Maximum number of webhook subscriptions allowed per user (default: 10).+# WEBHOOK_MAX_PER_USER=10+# =============================================================================# BACKGROUND PROCESSING# =============================================================================diff --git a/config/env.whisper.example b/config/env.whisper.exampleindex 4971fdf5..f664324f 100644--- a/config/env.whisper.example+++ b/config/env.whisper.example@@ -92,6 +92,14 @@ TRANSCRIPTION_MODEL=whisper-1# Legacy model name (deprecated, use TRANSCRIPTION_MODEL instead)# WHISPER_MODEL=whisper-1+# Comma-separated list of transcription model names offered in the per-upload+# model dropdown. Leave empty to hide the dropdown and always use the model+# configured above. Example: whisper-1,gpt-4o-transcribe,gpt-4o-transcribe-diarize+# TRANSCRIPTION_MODELS_AVAILABLE=++# Enable app-level chunking for the Mistral transcription connector (default: false).+# MISTRAL_ENABLE_CHUNKING=false+# --- Application Settings ---# Set to "true" to allow user registration, "false" to disableALLOW_REGISTRATION=false@@ -100,6 +108,15 @@ ALLOW_REGISTRATION=falseREGISTRATION_ALLOWED_DOMAINS=SUMMARY_MAX_TOKENS=8000CHAT_MAX_TOKENS=5000+# Max tokens for auto title generation (default: 5000)+# TITLE_MAX_TOKENS=5000+# Max tokens for event extraction (default: 3000)+# EVENT_MAX_TOKENS=3000++# --- Session Security ---+# Only send the session cookie over HTTPS. Set to true in HTTPS production+# deployments. Default: false (so plain-HTTP local setups keep working).+# SESSION_COOKIE_SECURE=false# Timezone for displaying dates and times in the UI# Use a valid TZ database name (e.g., "America/New_York", "Europe/London", "UTC")@@ -148,6 +165,20 @@ ADMIN_PASSWORD=changeme# Requires additional dependencies (already included in Docker image)ENABLE_INQUIRE_MODE=false+# Embedding model for Inquire-mode semantic search.+# Default is a local sentence-transformers model (no API needed).+# EMBEDDING_MODEL=all-MiniLM-L6-v2++# To use an OpenAI-compatible embeddings API instead of the local model,+# set the endpoint and API key below. When EMBEDDING_BASE_URL is set,+# Inquire embeddings are generated via the API instead of locally.+# EMBEDDING_BASE_URL=+# EMBEDDING_API_KEY=++# Optional fixed embedding dimensionality. Leave empty to auto-detect from+# the model/endpoint.+# EMBEDDING_DIMENSIONS=+# --- Automated File Processing (Black Hole Directory) ---# Set to "true" to enable automated file processingENABLE_AUTO_PROCESSING=false@@ -241,10 +272,41 @@ INCOGNITO_MODE_DEFAULT=false# Default: false (video uploads extract audio only, video stream is discarded)VIDEO_RETENTION=false+# --- Video Passthrough to ASR ---+# Send original video files directly to ASR without extracting audio.+# Useful for custom ASR backends that handle video internally (e.g., multi-track audio extraction).+# When enabled, video files bypass audio extraction, codec conversion, and chunking.+# Only affects video files — audio uploads are processed normally.+# Default: false+# VIDEO_PASSTHROUGH_ASR=false+# --- Concurrent Uploads ---# Maximum number of simultaneous file uploads (default: 3)MAX_CONCURRENT_UPLOADS=3+# --- Server-Side Recording Sessions (optional) ---+# Opt-in: in-app recordings stream audio chunks to the server as they record,+# instead of buffering the entire recording in browser RAM. This enables+# hours-long recordings and resume-on-reload if the tab is closed or refreshed.+# Default: false (recordings are buffered in the browser).+# ENABLE_SERVER_RECORDING_CHUNKS=false+#+# Absolute ceiling (in hours) on a single in-app recording when server+# chunking is enabled.+# RECORDING_MAX_HOURS=8+#+# Per-user soft storage cap (in bytes) for in-progress server recording+# sessions. Default: 5368709120 (5 GB).+# RECORDING_SESSION_MAX_BYTES_PER_USER=5368709120++# --- Webhooks (optional) ---+# Outbound webhooks notify external services when events occur. Configured+# per-user in the UI.+# Master kill-switch for outbound webhook delivery (default: true).+# WEBHOOK_GLOBAL_ENABLED=true+# Maximum number of webhook subscriptions allowed per user (default: 10).+# WEBHOOK_MAX_PER_USER=10+# --- Background Processing Queues ---# Separate queues for transcription (slow) and summary (fast) jobs# This prevents slow ASR jobs from blocking quick summary generationdiff --git a/docs/getting-started/installation.md b/docs/getting-started/installation.mdindex 5eb2a95c..1a889d9a 100644--- a/docs/getting-started/installation.md+++ b/docs/getting-started/installation.md@@ -349,6 +349,17 @@ MAX_CONCURRENT_UPLOADS=3 # defaultHigher values speed up batch uploads but use more bandwidth and server resources.+#### Server-Side Recording Sessions (optional)++By default, in-app recordings are buffered in the browser's memory and uploaded when you press Stop, which limits how long a single recording can run. You can opt into server-side recording sessions instead, where audio chunks stream to the server as they are produced:++```bash+ENABLE_SERVER_RECORDING_CHUNKS=true+RECORDING_MAX_HOURS=8 # default+```++When enabled, recordings are no longer constrained by browser RAM, so you can capture hours-long sessions, and an interrupted recording can resume if the tab is reloaded or closed. `RECORDING_MAX_HOURS` sets an absolute ceiling on a single recording (default 8 hours). For tuning the per-user storage cap and other details, see the [Server-Side Recording Sessions](../admin-guide/recording-sessions.md) guide.+#### Inquire Mode for Semantic SearchInquire Mode transforms Speakr from a simple transcription tool into a knowledge base of all your recordings. When enabled, you can search across all your transcriptions using natural language questions: