feat: transcription & AI - Whisper, summaries, task extraction #39
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
lucasheriques
force-pushed
the
feat/audio-04-transcription
branch
from
abc7825 to
5d4dfb5
Compare
lucasheriques
force-pushed
the
feat/audio-03-recording-ui
branch
from
aa12b0c to
715b152
Compare
lucasheriques
force-pushed
the
feat/audio-04-transcription
branch
from
5d4dfb5 to
9cfb638
Compare
lucasheriques
force-pushed
the
feat/audio-03-recording-ui
branch
from
715b152 to
36dd058
Compare
This was referenced Oct 17, 2025
Contributor
Author
This stack of pull requests is managed by Graphite. Learn more about stacking. |
lucasheriques
force-pushed
the
feat/audio-03-recording-ui
branch
from
36dd058 to
1093438
Compare
lucasheriques
force-pushed
the
feat/audio-04-transcription
branch
from
9cfb638 to
5510bfd
Compare
lucasheriques
force-pushed
the
feat/audio-03-recording-ui
branch
2 times, most recently
from
7800586 to
cb49c82
Compare
lucasheriques
force-pushed
the
feat/audio-04-transcription
branch
2 times, most recently
from
41e9a77 to
8115bff
Compare
joshsny
approved these changes
Oct 20, 2025
Contributor
joshsny
left a comment
joshsny
left a comment
There was a problem hiding this comment.
LGTM - I haven't run it locally, but code looks good, looking forward to merging this in and trying it out!
|
|
||
| return false; | ||
| // Check OpenAI key | ||
| if (state.encryptedOpenaiKey) { |
Contributor
There was a problem hiding this comment.
we can leave this for now if you want, but it'd probably be fairly simple to get this working through the gateway
| return resolvedPath.startsWith(recordingsDirResolved + path.sep); | ||
| } | ||
|
|
||
| async function generateTranscriptSummary( |
Contributor
There was a problem hiding this comment.
This should go through our llm gateway already, since that supports gpt-4o-mini, I think the AI SDK works fine with a proxy
7 tasks
graphite-app
bot
changed the base branch from
feat/audio-03-recording-ui
to
graphite-base/39
jonathanlab
approved these changes
Oct 22, 2025
Contributor
Author
- OpenAI Whisper transcription (gpt-4o-mini-transcribe) - Auto-generate 3-7 word summaries (GPT-4o-mini) - Extract actionable tasks from transcripts - TranscriptionSection UI component - SettingsPanel for OpenAI key management - Secure API key storage in authStore - 25MB file size limit handling
lucasheriques
force-pushed
the
feat/audio-04-transcription
branch
from
8115bff to
4da4f22
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Part 4/4 of audio recording feature stack.
Changes
Stack
Review notes
Completes the feature. Focus on AI prompts, error handling, and API key security.