NAOMS · building block
Speech
Speech recognition and text-to-speech for talking to your app.
Speech is the voice package: it turns spoken audio into text and back, handling recording, transcription and consent as separate steps. A local path runs speech-to-text and text-to-speech on the device and deletes the audio right after transcription, while a remote path for heavier processing requires an explicit consent grant first. Transcripts are written into the personal knowledge graph automatically, so a voice conversation becomes searchable like a typed note.
What a person notices
- Talking to the app works offline, with audio processed on the device and deleted right after.
- Nothing is sent anywhere else for processing unless the person has explicitly agreed to it.
- A voice conversation is searchable afterward, the same way a typed note would be.
What you get as a developer
Speech turns voice into text and text into voice, with the local path as the default and the remote path opt-in only.
- Two paths exist side by side: a fully local path with on-device speech-to-text and text-to-speech and no network calls at all, and a remote path for heavier processing that requires an explicit, checked consent grant before any audio is touched.
- On the local path, audio files are deleted immediately after transcription. Nothing lingers waiting to be cleaned up later.
- Transcriptions are stored automatically as memories in the personal knowledge graph, so a conversation held by voice becomes searchable the same way a typed note would.
- The remote path checks that an audio file actually lives in an allowed location before touching it, and filters out low-confidence transcription segments rather than passing along a guess as if it were certain.