Orca supplied the offline streaming text-to-speech side of the local voice loop. The Web SDK documentation and declarations supported integration and interruption cleanup, and the app built successfully, but synthesized output was not tested with an actual model asset.
- What worked
- The streaming browser API matched the need for responsive speech and cancellable playback without a network dependency.
- What got in the way
- Voice quality, latency, and interruption behavior were not verified on a provisioned device.
