llama.cpp
ui: voice messages and dictation with live waveforms and transcripts
#32531
Merged

ui: voice messages and dictation with live waveforms and transcripts #32531

allozaur
allozaur allozaur force pushed from 6fbc1c36 to bd5ddd7b 2 days ago
github-actions github-actions added documentation
github-actions github-actions added devops
github-actions github-actions added server/ui
allozaur allozaur force pushed from b86f6835 to d5a945ce 2 days ago
allozaur allozaur force pushed from 2c6d00da to 912f32c8 2 days ago
allozaur allozaur force pushed from defe60da to b4516fab 1 day ago
allozaur allozaur marked this pull request as ready for review 20 hours ago
allozaur allozaur requested a review 20 hours ago
allozaur allozaur requested a review 20 hours ago
allozaur allozaur requested a review from ggerganov ggerganov 19 hours ago
allozaur allozaur requested a review from ServeurpersoCom ServeurpersoCom 19 hours ago
allozaur allozaur requested a review from ngxson ngxson 19 hours ago
CISC
CISC approved these changes on 2026-11-20
allozaur allozaur force pushed from ab02fb55 to 6fa78b56 19 hours ago
github-actions github-actions added video demo
ServeurpersoCom
allozaur allozaur force pushed from 6fa78b56 to 69a320eb 18 hours ago
allozaur ui: add a voice engine for capture, peaks and transcription
58369fb8
allozaur ui: add voice waveform and transcript components to Llama UI
91b3e58b
allozaur ui: add stories and tests for the voice components
0b6052da
allozaur ui: store voice messages with their transcript and send it to models …
e55bfecc
allozaur ui: add Voice settings and resolve what the microphone does per model
3ea381cd
allozaur ui: record voice messages and dictation from the chat form
7a5d8adb
allozaur ui: draw audio attachments as playable waveforms with their transcript
5fffee01
allozaur ui: drop the old audio recorder and proxy realtime transcription in dev
14c908f8
allozaur ui: dictate with a model that is already loaded when the chat model c…
d0b4c779
allozaur ui: fill the recording waveform, and open voice message transcripts
ff88a4db
allozaur ui: record voice without ducking other audio, from the first word
47a110f1
allozaur ui: show voice text live in the message box, and follow transcripts a…
cd8c0771
allozaur ui: let the capture test start with silence
ecbc98e7
allozaur ui: show live voice text sooner, and keep silence from becoming "yeah"
832b2148
allozaur ui: transcribe a recording cut at pauses once more as a whole
12c3e4f7
allozaur ui: give live text over HTTP for models without a realtime session
90661032
allozaur ui: say when the browser processes the microphone despite the raw req…
7392246d
allozaur ui: keep the microphone beside the stop and send buttons
d8b158bc
allozaur ui: show the voice components' stories with Llama UI
0a53262f
allozaur ui: add a noise suppression setting for voice input
5aaa447d
allozaur ui: keep live voice text coming when the room is never quiet
9c5ee835
allozaur ui: add echo cancellation and automatic gain settings for voice input
228b2256
allozaur ui: put the microphone after the stop button, filled like it
9f3c6a52
allozaur ui: say when dictated text is being refined, and send it refined
ee7b23ae
allozaur ui: keep the send button in place and put the microphone beside it
69fe9d93
allozaur ui: let a recording be sent while a reply streams, once it has words
163610b4
allozaur ui: raise quiet speech for transcription, and say when it is too quiet
bef4a07a
allozaur ui: keep the voice engine free of app code
dbc9809d
allozaur ui: start voice sessions from one voice service
b8cbca94
allozaur ui: tell speech from the room in one place
ef3f201c
allozaur ui: let any text field take dictation
3f8ef65f
allozaur ui: move the recording row into Llama UI
6011b740
allozaur ui: keep the voice engine's Svelte recorder behind its own entry
525fc5aa
allozaur ui: move voice input into its own package, Llama Voice
0ef6a25c
allozaur ui: show which model does what in voice input
4bfc0153
allozaur ui: warn of a quiet microphone inside the recording row
262cdf23
allozaur ui: open the microphone while the pointer is on its button
33887448
allozaur ui: tidy voice input after review
05e704f1
allozaur ui: pin Llama Voice's dev dependencies to Llama UI's versions
49144bf6
allozaur ui: let demos speak into a synthetic microphone
21395cd6
allozaur ui: keep the microphone for voice input, off the audio files entry
25fcc2aa
allozaur ui: set voice input on the slimmed design tokens
ae571b19
allozaur allozaur force pushed from 69a320eb to ae571b19 18 hours ago
allozaur
allozaur commented on 2026-11-20
allozaur
allozaur commented on 2026-11-20
allozaur ui: name voice states, platform strings, patterns and tunings
3927a837
allozaur ui: keep all of Llama UI's tests under tests
8a87b13a
ServeurpersoCom
ServeurpersoCom
allozaur ui: show a transcript's words without the model's own format
c6e0c1e2
allozaur ui: dictate when a speech-to-text model is picked for the conversation
d0fe3fa6
allozaur ui: say why a live-only model cannot transcribe behind an API key
9b198402
ngxson
ngxson approved these changes on 2026-11-20
allozaur
allozaur ui: pick the dictation model with a microphone on its row
eebea0c8
ServeurpersoCom
ServeurpersoCom approved these changes on 2026-11-20
ServeurpersoCom
allozaur allozaur merged 79e81b0b into master 13 hours ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone