RealtimeSTT 0.3.104

Features & Improvements

• New parameter: start_callback_in_new_thread
  If set to True, all callback functions will be executed in a new thread.
  This can be useful if the callback function is blocking and you want to avoid blocking the realtimestt application thread.

RealtimeSTT 0.3.103

Features & Improvements

• Thread‑safe IPC: Introduce SafePipe to replace mp.Pipe, hopefully ensuring robust inter-process communication (needs more tests).
• Audio normalization: New normalize_audio option scales input to –0.95 dBFS for consistent transcription quality.
• Callback overhaul: All event callbacks (VAD, wake‑word, turn detection, recording, realtime updates) now run asynchronously via helper threads.
• Wake word & VAD: Add wakeword_backend config and faster_whisper_vad_filter flag; improved error messages when misconfigured.
• Rich metadata: Embed nanosecond‑precision timestamps in both client and server, serialized as formatted strings.
• CLI enhancements: --faster_whisper_vad_filter and --debug_websockets flags give finer control over server behavior.
• Testing updates: Adjusted parameters in realtimestt_test and added a new type_into_textbox.py example.

RealtimeSTT 0.3.101

✨ Features & Improvements

• Enhanced Real-time Responsiveness: Real-time transcription processing now intelligently pauses immediately when VAD detects silence, reducing latency and unnecessary work before the final transcription.
• Client Connection Robustness: Using a more accurate WebSocket-based server check.
• Remote Wake Word Delay Config: Clients can now configure the wake_word_activation_delay on the server.
• Updated OpenAI Example: Refreshed the openai_voice_interface.py example with the latest OpenAI API, EdgeEngine TTS, configuration flags, and graceful shutdown.

RealtimeSTT 0.3.100

New VAD callbacks on_vad_start and on_vad_stop

• triggering on VAD presence
• reverted functionality of on_vad_detect_start, on_vad_detect_stop back to: triggered when the system starts/stops detecting for VAD presence

RealtimeSTT 0.3.99

1. Enhanced Logging Configuration

• Introduced a dedicated named logger realtimestt instead of using the root logger.
• Added structured logging with handlers for both console (level set by user) and file (always DEBUG).
• Logging no longer propagates to the root logger by default (logger.propagate = False).

2. Added possibility to disable Faster-Whisper VAD Filter

• Added faster_whisper_vad_filter parameter (default: True) to enable voice activity detection (VAD) from the faster_whisper library.
• Improves robustness against background noise at the cost of additional GPU resources.
• Integrated into both real-time and main transcription workflows.

3. Audio Worker Improvements

• Added improved, detailed debug logging for audio device initialization, sample rate handling, and resampling.

4. VAD Callback Adjustments

• fixes #215
• Moved on_vad_detect_start and on_vad_detect_stop callbacks to trigger directly during voice activity checks instead of state transitions.
• Ensures callbacks align more accurately with actual speech/silence events.

RealtimeSTT 0.3.98

• minor fix for pypi wheel

RealtimeSTT 0.3.97

• fix for #210

RealtimeSTT 0.3.95

• better warmup (using audio file)
• merged #200

RealtimeSTT 0.3.94

• New Parameters for stop-method of AudioToTextRecorder:

  • backdate_stop_seconds (float, default=0.0):

    • Description: Specifies the number of seconds to backdate the stop time when ending a recording.
    • Usage: When invoking stop() due to a wake word detection or a speaker diarization change event, this parameter compensates for any latency, ensuring that only relevant audio is included in the recording and transcription.

  • backdate_resume_seconds (float, default=0.0):

    • Description: Specifies the number of seconds to backdate the resume time when restarting listening after a recording has stopped.
    • Usage: Typically set to the same value as backdate_stop_seconds, this parameter allows for fine-tuning.

• fix for stt-server (got broken by webservers dependency upgrade because of an api change)
• added initial_prompt_realtime to AudioToTextRecorder to be able to give different prompts to final and realtime model
• added new parameters to client/server (download root, batch sizes)