open-agents-ai 0.19.1 → 0.20.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +8 -3
  2. package/dist/index.js +304 -279
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -121,7 +121,11 @@ All proposals are indexed in `.oa/dreams/PROPOSAL-INDEX.md` for easy review.
121
121
 
122
122
  ## Listen Mode — Live Bidirectional Audio
123
123
 
124
- Listen mode enables real-time voice communication with the agent. Your microphone audio is captured, streamed through Whisper (via `transcribe-cli`), and the transcription is injected directly into the input line — creating a hands-free coding workflow.
124
+ Listen mode enables real-time voice communication with the agent. Your microphone audio is captured, streamed through Whisper, and the transcription is injected directly into the input line — creating a hands-free coding workflow.
125
+
126
+ Two transcription backends ensure broad platform support:
127
+ - **transcribe-cli** (faster-whisper / ONNX) — used by default, fastest on x86
128
+ - **openai-whisper** (Python venv) — automatic fallback for ARM, linux-arm64, or when ONNX is unavailable. Auto-creates a venv and installs deps on first use.
125
129
 
126
130
  ```bash
127
131
  /listen # Toggle microphone capture on/off
@@ -143,10 +147,11 @@ Listen mode enables real-time voice communication with the agent. Your microphon
143
147
  When combined with `/voice`, you get full bidirectional audio — speak your tasks, hear the agent's progress through TTS, and speak corrections mid-task. The status bar shows a blinking red `● REC` indicator with a countdown timer during auto-mode recording.
144
148
 
145
149
  **Platform support:**
146
- - **Linux**: `arecord` (ALSA) or `ffmpeg` (PulseAudio)
150
+ - **Linux x86**: `arecord` (ALSA) or `ffmpeg` (PulseAudio) + transcribe-cli
151
+ - **Linux ARM**: `arecord` or `ffmpeg` + openai-whisper (auto-installed in Python venv)
147
152
  - **macOS**: `sox` (CoreAudio) or `ffmpeg` (AVFoundation)
148
153
 
149
- The `transcribe-cli` dependency auto-installs in the background on first use.
154
+ The `transcribe-cli` dependency auto-installs in the background on first use. On ARM or when transcribe-cli fails, the system automatically falls back to `openai-whisper` via a self-managed Python venv (same approach used by Moondream vision).
150
155
 
151
156
  **File transcription**: Drag-and-drop audio/video files (`.mp3`, `.wav`, `.mp4`, `.mkv`, etc.) onto the terminal to transcribe them. Results are saved to `.oa/transcripts/`.
152
157