Merge pull request #59 from cjpais/recording-pill

Add Recording Overlay
This commit is contained in:
CJ Pais 2025-08-01 15:35:11 -07:00 committed by GitHub
commit 6ce848dc66
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
31 changed files with 1904 additions and 19 deletions

BIN
bun.lockb

Binary file not shown.

1273
package-lock.json generated Normal file

File diff suppressed because it is too large Load diff

View file

@ -14,6 +14,7 @@
"@tauri-apps/api": "^2.6.0",
"@tauri-apps/plugin-autostart": "~2",
"@tauri-apps/plugin-clipboard-manager": "~2",
"@tauri-apps/plugin-fs": "~2",
"@tauri-apps/plugin-global-shortcut": "~2",
"@tauri-apps/plugin-opener": "^2",
"@tauri-apps/plugin-os": "~2",

BIN
public/icon/recording.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.4 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.5 KiB

29
src-tauri/Cargo.lock generated
View file

@ -2018,12 +2018,14 @@ dependencies = [
"reqwest 0.11.27",
"rodio",
"rubato",
"rustfft",
"serde",
"serde_json",
"tauri",
"tauri-build",
"tauri-plugin-autostart",
"tauri-plugin-clipboard-manager",
"tauri-plugin-fs",
"tauri-plugin-global-shortcut",
"tauri-plugin-macos-permissions",
"tauri-plugin-opener",
@ -4403,9 +4405,9 @@ dependencies = [
[[package]]
name = "rustfft"
version = "6.2.0"
version = "6.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "43806561bc506d0c5d160643ad742e3161049ac01027b5e6d7524091fd401d86"
checksum = "c6f140db74548f7c9d7cce60912c9ac414e74df5e718dc947d514b051b42f3f4"
dependencies = [
"num-complex",
"num-integer",
@ -4413,7 +4415,6 @@ dependencies = [
"primal-check",
"strength_reduce",
"transpose",
"version_check",
]
[[package]]
@ -5450,6 +5451,28 @@ dependencies = [
"thiserror 2.0.11",
]
[[package]]
name = "tauri-plugin-fs"
version = "2.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8c6ef84ee2f2094ce093e55106d90d763ba343fad57566992962e8f76d113f99"
dependencies = [
"anyhow",
"dunce",
"glob",
"percent-encoding",
"schemars",
"serde",
"serde_json",
"serde_repr",
"tauri",
"tauri-plugin",
"tauri-utils",
"thiserror 2.0.11",
"toml",
"url",
]
[[package]]
name = "tauri-plugin-global-shortcut"
version = "2.2.0"

View file

@ -28,7 +28,7 @@ tauri-build = { version = "2", features = [] }
[dependencies]
once_cell = "1"
tauri = { version = "2", features = ["tray-icon", 'image-png'] }
tauri = { version = "2", features = [ "macos-private-api", "tray-icon", 'image-png'] }
tauri-plugin-opener = "2"
serde = { version = "1", features = ["derive"] }
serde_json = "1"
@ -51,6 +51,8 @@ tauri-plugin-process = "2"
rodio = { git = "https://github.com/cjpais/rodio.git" }
reqwest = { version = "0.11", features = ["json", "stream"] }
futures-util = "0.3"
tauri-plugin-fs = "2"
rustfft = "6.4.0"
[dependencies.ort-sys]
version = "=2.0.0-rc.9"

View file

@ -1,8 +1,8 @@
{
"$schema": "../gen/schemas/desktop-schema.json",
"identifier": "default",
"description": "Capability for the main window",
"windows": ["main"],
"description": "Capabilities for the app",
"windows": ["main", "recording_overlay"],
"permissions": [
"core:default",
"opener:default",
@ -13,6 +13,8 @@
"global-shortcut:allow-register",
"global-shortcut:allow-unregister",
"global-shortcut:allow-unregister-all",
"macos-permissions:default"
"macos-permissions:default",
"fs:read-files",
"fs:allow-resource-read-recursive"
]
}

View file

@ -0,0 +1,17 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>NSPrivacyAccessedAPITypes</key>
<array>
<dict>
<key>NSPrivacyAccessedAPIType</key>
<string>NSPrivacyAccessedAPICategoryFileTimestamp</string>
<key>NSPrivacyAccessedAPITypeReasons</key>
<array>
<string>C617.1</string>
</array>
</dict>
</array>
</dict>
</plist>

View file

@ -5,6 +5,8 @@ use crate::utils;
use crate::utils::change_tray_icon;
use crate::utils::play_recording_start_sound;
use crate::utils::play_recording_stop_sound;
use crate::utils::show_recording_overlay;
use crate::utils::show_transcribing_overlay;
use crate::utils::TrayIconState;
use log::debug;
use once_cell::sync::Lazy;
@ -30,6 +32,7 @@ impl ShortcutAction for TranscribeAction {
let binding_id = binding_id.to_string();
change_tray_icon(app, TrayIconState::Recording);
show_recording_overlay(app);
let rm = app.state::<Arc<AudioRecordingManager>>();
@ -78,6 +81,7 @@ impl ShortcutAction for TranscribeAction {
let tm = Arc::clone(&app.state::<Arc<TranscriptionManager>>());
change_tray_icon(app, TrayIconState::Transcribing);
show_transcribing_overlay(app);
// Play audio feedback for recording stop
play_recording_stop_sound(app);
@ -119,23 +123,29 @@ impl ShortcutAction for TranscribeAction {
),
Err(e) => eprintln!("Failed to paste transcription: {}", e),
}
// Hide the overlay after transcription is complete
utils::hide_recording_overlay(&ah_clone);
change_tray_icon(&ah_clone, TrayIconState::Idle);
})
.unwrap_or_else(|e| {
eprintln!("Failed to run paste on main thread: {:?}", e);
utils::hide_recording_overlay(&ah);
change_tray_icon(&ah, TrayIconState::Idle);
});
} else {
utils::hide_recording_overlay(&ah);
change_tray_icon(&ah, TrayIconState::Idle);
}
}
Err(err) => {
debug!("Global Shortcut Transcription error: {}", err);
utils::hide_recording_overlay(&ah);
change_tray_icon(&ah, TrayIconState::Idle);
},
}
}
} else {
debug!("No samples retrieved from recording stop");
utils::hide_recording_overlay(&ah);
change_tray_icon(&ah, TrayIconState::Idle);
}
});

View file

@ -2,7 +2,9 @@
mod device;
mod recorder;
mod resampler;
mod visualizer;
pub use device::{list_input_devices, list_output_devices, CpalDeviceInfo};
pub use recorder::AudioRecorder;
pub use resampler::FrameResampler;
pub use visualizer::AudioVisualiser;

View file

@ -10,7 +10,7 @@ use cpal::{
};
use crate::audio_toolkit::{
audio::FrameResampler,
audio::{AudioVisualiser, FrameResampler},
constants,
vad::{self, VadFrame},
VoiceActivityDetector,
@ -27,6 +27,7 @@ pub struct AudioRecorder {
cmd_tx: Option<mpsc::Sender<Cmd>>,
worker_handle: Option<std::thread::JoinHandle<()>>,
vad: Option<Arc<Mutex<Box<dyn vad::VoiceActivityDetector>>>>,
level_cb: Option<Arc<dyn Fn(Vec<f32>) + Send + Sync + 'static>>,
}
impl AudioRecorder {
@ -36,6 +37,7 @@ impl AudioRecorder {
cmd_tx: None,
worker_handle: None,
vad: None,
level_cb: None,
})
}
@ -44,6 +46,14 @@ impl AudioRecorder {
self
}
pub fn with_level_callback<F>(mut self, cb: F) -> Self
where
F: Fn(Vec<f32>) + Send + Sync + 'static,
{
self.level_cb = Some(Arc::new(cb));
self
}
pub fn open(&mut self, device: Option<Device>) -> Result<(), Box<dyn std::error::Error>> {
if self.worker_handle.is_some() {
return Ok(()); // already open
@ -62,6 +72,8 @@ impl AudioRecorder {
let thread_device = device.clone();
let vad = self.vad.clone();
// Move the optional level callback into the worker thread
let level_cb = self.level_cb.clone();
let worker = std::thread::spawn(move || {
let config = AudioRecorder::get_preferred_config(&thread_device)
@ -105,7 +117,7 @@ impl AudioRecorder {
stream.play().expect("failed to start stream");
// keep the stream alive while we process samples
run_consumer(sample_rate, vad, sample_rx, cmd_rx);
run_consumer(sample_rate, vad, sample_rx, cmd_rx, level_cb);
// stream is dropped here, after run_consumer returns
});
@ -215,6 +227,7 @@ fn run_consumer(
vad: Option<Arc<Mutex<Box<dyn vad::VoiceActivityDetector>>>>,
sample_rx: mpsc::Receiver<Vec<f32>>,
cmd_rx: mpsc::Receiver<Cmd>,
level_cb: Option<Arc<dyn Fn(Vec<f32>) + Send + Sync + 'static>>,
) {
let mut frame_resampler = FrameResampler::new(
in_sample_rate as usize,
@ -225,6 +238,17 @@ fn run_consumer(
let mut processed_samples = Vec::<f32>::new();
let mut recording = false;
// ---------- spectrum visualisation setup ---------------------------- //
const BUCKETS: usize = 16;
const WINDOW_SIZE: usize = 512;
let mut visualizer = AudioVisualiser::new(
in_sample_rate,
WINDOW_SIZE,
BUCKETS,
80.0, // vocal_min_hz
4000.0, // vocal_max_hz
);
fn handle_frame(
samples: &[f32],
recording: bool,
@ -252,6 +276,14 @@ fn run_consumer(
Err(_) => break, // stream closed
};
// ---------- spectrum processing ---------------------------------- //
if let Some(buckets) = visualizer.feed(&raw) {
if let Some(cb) = &level_cb {
cb(buckets);
}
}
// ---------- existing pipeline ------------------------------------ //
frame_resampler.push(&raw, &mut |frame: &[f32]| {
handle_frame(frame, recording, &vad, &mut processed_samples)
});
@ -262,6 +294,7 @@ fn run_consumer(
Cmd::Start => {
processed_samples.clear();
recording = true;
visualizer.reset(); // Reset visualization buffer
if let Some(v) = &vad {
v.lock().unwrap().reset();
}

View file

@ -0,0 +1,156 @@
use rustfft::{num_complex::Complex32, Fft, FftPlanner};
use std::sync::Arc;
const DB_MIN: f32 = -55.0;
const DB_MAX: f32 = -8.0;
const GAIN: f32 = 1.3;
const CURVE_POWER: f32 = 0.7;
pub struct AudioVisualiser {
fft: Arc<dyn Fft<f32>>,
window: Vec<f32>,
bucket_ranges: Vec<(usize, usize)>,
fft_input: Vec<Complex32>,
noise_floor: Vec<f32>,
buffer: Vec<f32>,
window_size: usize,
buckets: usize,
}
impl AudioVisualiser {
pub fn new(
sample_rate: u32,
window_size: usize,
buckets: usize,
freq_min: f32,
freq_max: f32,
) -> Self {
let mut planner = FftPlanner::<f32>::new();
let fft = planner.plan_fft_forward(window_size);
// Pre-compute Hann window
let window: Vec<f32> = (0..window_size)
.map(|i| {
0.5 * (1.0 - (2.0 * std::f32::consts::PI * i as f32 / window_size as f32).cos())
})
.collect();
// Pre-compute bucket frequency ranges
let nyquist = sample_rate as f32 / 2.0;
let freq_min = freq_min.min(nyquist);
let freq_max = freq_max.min(nyquist);
let mut bucket_ranges = Vec::with_capacity(buckets);
for b in 0..buckets {
// Use logarithmic spacing for better perceptual representation
let log_start = (b as f32 / buckets as f32).powi(2);
let log_end = ((b + 1) as f32 / buckets as f32).powi(2);
let start_hz = freq_min + (freq_max - freq_min) * log_start;
let end_hz = freq_min + (freq_max - freq_min) * log_end;
let start_bin = ((start_hz * window_size as f32) / sample_rate as f32) as usize;
let mut end_bin = ((end_hz * window_size as f32) / sample_rate as f32) as usize;
// Ensure each bucket has at least one bin
if end_bin <= start_bin {
end_bin = start_bin + 1;
}
// Clamp to valid range
let start_bin = start_bin.min(window_size / 2);
let end_bin = end_bin.min(window_size / 2);
bucket_ranges.push((start_bin, end_bin));
}
Self {
fft,
window,
bucket_ranges,
fft_input: vec![Complex32::new(0.0, 0.0); window_size],
noise_floor: vec![-40.0; buckets], // Initialize to reasonable noise floor
buffer: Vec::with_capacity(window_size * 2),
window_size,
buckets,
}
}
pub fn feed(&mut self, samples: &[f32]) -> Option<Vec<f32>> {
// Add new samples to buffer
self.buffer.extend_from_slice(samples);
// Only process if we have enough samples
if self.buffer.len() < self.window_size {
return None;
}
// Take the required window of samples
let window_samples = &self.buffer[..self.window_size];
// Remove DC component
let mean = window_samples.iter().sum::<f32>() / self.window_size as f32;
// Apply window function and prepare FFT input
for (i, &sample) in window_samples.iter().enumerate() {
let windowed_sample = (sample - mean) * self.window[i];
self.fft_input[i] = Complex32::new(windowed_sample, 0.0);
}
// Perform FFT
self.fft.process(&mut self.fft_input);
// Compute power spectrum and bucket levels
let mut buckets = vec![0.0; self.buckets];
for (bucket_idx, &(start_bin, end_bin)) in self.bucket_ranges.iter().enumerate() {
if start_bin >= end_bin || end_bin > self.fft_input.len() / 2 {
continue;
}
// Calculate average power in this frequency range
let mut power_sum = 0.0;
for bin_idx in start_bin..end_bin {
let magnitude = self.fft_input[bin_idx].norm();
power_sum += magnitude * magnitude;
}
let avg_power = power_sum / (end_bin - start_bin) as f32;
// Convert to dB with proper scaling
let db = if avg_power > 1e-12 {
20.0 * (avg_power.sqrt() / self.window_size as f32).log10()
} else {
-80.0 // Very low floor for zero power
};
// Only update noise floor when signal is quiet (below current floor + 10dB)
if db < self.noise_floor[bucket_idx] + 10.0 {
const NOISE_ALPHA: f32 = 0.001; // Very slow adaptation
self.noise_floor[bucket_idx] =
NOISE_ALPHA * db + (1.0 - NOISE_ALPHA) * self.noise_floor[bucket_idx];
}
// Map configurable dB range to 0-1 with gain and curve shaping
let normalized = ((db - DB_MIN) / (DB_MAX - DB_MIN)).clamp(0.0, 1.0);
buckets[bucket_idx] = (normalized * GAIN).powf(CURVE_POWER).clamp(0.0, 1.0);
}
// Apply light smoothing to reduce jitter
for i in 1..buckets.len() - 1 {
buckets[i] = buckets[i] * 0.7 + buckets[i - 1] * 0.15 + buckets[i + 1] * 0.15;
}
// Clear processed samples from buffer
self.buffer.clear();
Some(buckets)
}
pub fn reset(&mut self) {
self.buffer.clear();
// Reset noise floor to initial values
self.noise_floor.fill(-40.0);
}
}

View file

@ -60,6 +60,7 @@ pub fn run() {
env_logger::init();
tauri::Builder::default()
.plugin(tauri_plugin_fs::init())
.plugin(tauri_plugin_process::init())
.plugin(tauri_plugin_updater::Builder::new().build())
.plugin(tauri_plugin_os::init())
@ -126,6 +127,9 @@ pub fn run() {
app.manage(model_manager.clone());
app.manage(transcription_manager.clone());
// Create the recording overlay window (hidden by default)
utils::create_recording_overlay(&app.handle());
shortcut::init_shortcuts(app);
Ok(())
@ -153,6 +157,7 @@ pub fn run() {
shortcut::change_audio_feedback_setting,
shortcut::change_translate_to_english_setting,
shortcut::change_selected_language_setting,
shortcut::change_show_overlay_setting,
trigger_update_check,
commands::cancel_operation,
commands::models::get_available_models,

View file

@ -1,5 +1,6 @@
use crate::audio_toolkit::{list_input_devices, vad::SmoothedVad, AudioRecorder, SileroVad};
use crate::settings::get_settings;
use crate::utils;
use log::{debug, info};
use std::sync::{Arc, Mutex};
use std::time::Instant;
@ -23,13 +24,26 @@ pub enum MicrophoneMode {
/* ──────────────────────────────────────────────────────────────── */
fn create_audio_recorder(vad_path: &str) -> Result<AudioRecorder, anyhow::Error> {
fn create_audio_recorder(
vad_path: &str,
app_handle: &tauri::AppHandle,
) -> Result<AudioRecorder, anyhow::Error> {
let silero = SileroVad::new(vad_path, 0.3)
.map_err(|e| anyhow::anyhow!("Failed to create SileroVad: {}", e))?;
let smoothed_vad = SmoothedVad::new(Box::new(silero), 15, 15, 2);
// Recorder with VAD plus a spectrum-level callback that forwards updates to
// the frontend.
let recorder = AudioRecorder::new()
.map_err(|e| anyhow::anyhow!("Failed to create AudioRecorder: {}", e))?
.with_vad(Box::new(smoothed_vad));
.with_vad(Box::new(smoothed_vad))
.with_level_callback({
let app_handle = app_handle.clone();
move |levels| {
utils::emit_levels(&app_handle, &levels);
}
});
Ok(recorder)
}
@ -97,7 +111,10 @@ impl AudioRecordingManager {
let mut recorder_opt = self.recorder.lock().unwrap();
if recorder_opt.is_none() {
*recorder_opt = Some(create_audio_recorder(vad_path.to_str().unwrap())?);
*recorder_opt = Some(create_audio_recorder(
vad_path.to_str().unwrap(),
&self.app_handle,
)?);
}
// Get the selected device from settings

View file

@ -30,6 +30,8 @@ pub struct AppSettings {
pub translate_to_english: bool,
#[serde(default = "default_selected_language")]
pub selected_language: String,
#[serde(default = "default_show_overlay")]
pub show_overlay: bool,
}
fn default_model() -> String {
@ -54,6 +56,11 @@ fn default_selected_language() -> String {
"auto".to_string()
}
fn default_show_overlay() -> bool {
// Default to true - users expect visual feedback by default
true
}
pub const SETTINGS_STORE_PATH: &str = "settings_store.json";
pub fn get_default_settings() -> AppSettings {
@ -99,6 +106,7 @@ pub fn get_default_settings() -> AppSettings {
selected_output_device: None,
translate_to_english: false,
selected_language: "auto".to_string(),
show_overlay: true,
}
}

View file

@ -127,6 +127,14 @@ pub fn change_selected_language_setting(app: AppHandle, language: String) -> Res
Ok(())
}
#[tauri::command]
pub fn change_show_overlay_setting(app: AppHandle, enabled: bool) -> Result<(), String> {
let mut settings = settings::get_settings(&app);
settings.show_overlay = enabled;
settings::write_settings(&app, settings);
Ok(())
}
fn _register_shortcut(app: &AppHandle, binding: ShortcutBinding) -> Result<(), String> {
// Parse shortcut and return error if it fails
let shortcut = match binding.current_binding.parse::<Shortcut>() {

View file

@ -6,6 +6,7 @@ use enigo::Keyboard;
use enigo::Settings;
use cpal::traits::{DeviceTrait, HostTrait};
use log::debug;
use rodio::OutputStreamBuilder;
use std::fs::File;
use std::io::BufReader;
@ -13,8 +14,7 @@ use std::thread;
use tauri::image::Image;
use tauri::menu::{Menu, MenuItem, PredefinedMenuItem};
use tauri::tray::TrayIcon;
use tauri::AppHandle;
use tauri::Manager;
use tauri::{AppHandle, Emitter, Manager, WebviewWindowBuilder};
use tauri_plugin_clipboard_manager::ClipboardExt;
fn send_paste() -> Result<(), String> {
@ -310,3 +310,107 @@ fn play_audio_file(
Ok(())
}
/* ──────────────────────────────────────────────────────────────── */
/* OVERLAY MANAGEMENT */
/* ──────────────────────────────────────────────────────────────── */
/// Creates the recording overlay window and keeps it hidden by default
pub fn create_recording_overlay(app_handle: &AppHandle) {
// Get screen dimensions for positioning
if let Ok(monitors) = app_handle.primary_monitor() {
if let Some(monitor) = monitors {
let size = monitor.size();
let scale = monitor.scale_factor();
let screen_width = (size.width as f64 / scale) as i32;
let screen_height = (size.height as f64 / scale) as i32;
// Position at bottom center, 30px from bottom
let x = (screen_width - 150) / 2;
let y = screen_height - 30 - 30;
match WebviewWindowBuilder::new(
app_handle,
"recording_overlay",
tauri::WebviewUrl::App("src/overlay/index.html".into()),
)
.title("Recording")
.position(x as f64, y as f64)
.resizable(false)
.maximizable(false)
.minimizable(false)
.closable(false)
.decorations(false)
.always_on_top(true)
.skip_taskbar(true)
.transparent(true)
.focused(false)
.visible(false) // Start hidden
.build()
{
Ok(_window) => {
debug!("Recording overlay window created successfully (hidden)");
}
Err(e) => {
debug!("Failed to create recording overlay window: {}", e);
}
}
}
}
}
/// Shows the recording overlay window with fade-in animation
pub fn show_recording_overlay(app_handle: &AppHandle) {
// Check if show_overlay is enabled in settings
let settings = settings::get_settings(app_handle);
if !settings.show_overlay {
return;
}
if let Some(overlay_window) = app_handle.get_webview_window("recording_overlay") {
let _ = overlay_window.show();
// Emit event to trigger fade-in animation with recording state
let _ = overlay_window.emit("show-overlay", "recording");
}
}
/// Shows the transcribing overlay window
pub fn show_transcribing_overlay(app_handle: &AppHandle) {
// Check if show_overlay is enabled in settings
let settings = settings::get_settings(app_handle);
if !settings.show_overlay {
return;
}
if let Some(overlay_window) = app_handle.get_webview_window("recording_overlay") {
let _ = overlay_window.show();
// Emit event to switch to transcribing state
let _ = overlay_window.emit("show-overlay", "transcribing");
}
}
/// Hides the recording overlay window with fade-out animation
pub fn hide_recording_overlay(app_handle: &AppHandle) {
// Check if show_overlay is enabled in settings - if disabled, the overlay shouldn't be shown anyway
// but we still want to hide it in case the setting was changed while recording
if let Some(overlay_window) = app_handle.get_webview_window("recording_overlay") {
// Emit event to trigger fade-out animation
let _ = overlay_window.emit("hide-overlay", ());
// Hide the window after a short delay to allow animation to complete
let window_clone = overlay_window.clone();
std::thread::spawn(move || {
std::thread::sleep(std::time::Duration::from_millis(300));
let _ = window_clone.hide();
});
}
}
pub fn emit_levels(app_handle: &AppHandle, levels: &Vec<f32>) {
// emit levels to main app
let _ = app_handle.emit("mic-level", levels);
// also emit to the recording overlay if it's open
if let Some(overlay_window) = app_handle.get_webview_window("recording_overlay") {
let _ = overlay_window.emit("mic-level", levels);
}
}

View file

@ -10,13 +10,14 @@
"frontendDist": "../dist"
},
"app": {
"macOSPrivateApi": true,
"windows": [
{
"title": "Handy",
"width": 540,
"height": 680,
"height": 720,
"minWidth": 540,
"minHeight": 680,
"minHeight": 720,
"resizable": true,
"maximizable": false
}

View file

@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="iconify iconify--logos" width="35.93" height="32" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 228"><path fill="#00D8FF" d="M210.483 73.824a171.49 171.49 0 0 0-8.24-2.597c.465-1.9.893-3.777 1.273-5.621c6.238-30.281 2.16-54.676-11.769-62.708c-13.355-7.7-35.196.329-57.254 19.526a171.23 171.23 0 0 0-6.375 5.848a155.866 155.866 0 0 0-4.241-3.917C100.759 3.829 77.587-4.822 63.673 3.233C50.33 10.957 46.379 33.89 51.995 62.588a170.974 170.974 0 0 0 1.892 8.48c-3.28.932-6.445 1.924-9.474 2.98C17.309 83.498 0 98.307 0 113.668c0 15.865 18.582 31.778 46.812 41.427a145.52 145.52 0 0 0 6.921 2.165a167.467 167.467 0 0 0-2.01 9.138c-5.354 28.2-1.173 50.591 12.134 58.266c13.744 7.926 36.812-.22 59.273-19.855a145.567 145.567 0 0 0 5.342-4.923a168.064 168.064 0 0 0 6.92 6.314c21.758 18.722 43.246 26.282 56.54 18.586c13.731-7.949 18.194-32.003 12.4-61.268a145.016 145.016 0 0 0-1.535-6.842c1.62-.48 3.21-.974 4.76-1.488c29.348-9.723 48.443-25.443 48.443-41.52c0-15.417-17.868-30.326-45.517-39.844Zm-6.365 70.984c-1.4.463-2.836.91-4.3 1.345c-3.24-10.257-7.612-21.163-12.963-32.432c5.106-11 9.31-21.767 12.459-31.957c2.619.758 5.16 1.557 7.61 2.4c23.69 8.156 38.14 20.213 38.14 29.504c0 9.896-15.606 22.743-40.946 31.14Zm-10.514 20.834c2.562 12.94 2.927 24.64 1.23 33.787c-1.524 8.219-4.59 13.698-8.382 15.893c-8.067 4.67-25.32-1.4-43.927-17.412a156.726 156.726 0 0 1-6.437-5.87c7.214-7.889 14.423-17.06 21.459-27.246c12.376-1.098 24.068-2.894 34.671-5.345a134.17 134.17 0 0 1 1.386 6.193ZM87.276 214.515c-7.882 2.783-14.16 2.863-17.955.675c-8.075-4.657-11.432-22.636-6.853-46.752a156.923 156.923 0 0 1 1.869-8.499c10.486 2.32 22.093 3.988 34.498 4.994c7.084 9.967 14.501 19.128 21.976 27.15a134.668 134.668 0 0 1-4.877 4.492c-9.933 8.682-19.886 14.842-28.658 17.94ZM50.35 144.747c-12.483-4.267-22.792-9.812-29.858-15.863c-6.35-5.437-9.555-10.836-9.555-15.216c0-9.322 13.897-21.212 37.076-29.293c2.813-.98 5.757-1.905 8.812-2.773c3.204 10.42 7.406 21.315 12.477 32.332c-5.137 11.18-9.399 22.249-12.634 32.792a134.718 134.718 0 0 1-6.318-1.979Zm12.378-84.26c-4.811-24.587-1.616-43.134 6.425-47.789c8.564-4.958 27.502 2.111 47.463 19.835a144.318 144.318 0 0 1 3.841 3.545c-7.438 7.987-14.787 17.08-21.808 26.988c-12.04 1.116-23.565 2.908-34.161 5.309a160.342 160.342 0 0 1-1.76-7.887Zm110.427 27.268a347.8 347.8 0 0 0-7.785-12.803c8.168 1.033 15.994 2.404 23.343 4.08c-2.206 7.072-4.956 14.465-8.193 22.045a381.151 381.151 0 0 0-7.365-13.322Zm-45.032-43.861c5.044 5.465 10.096 11.566 15.065 18.186a322.04 322.04 0 0 0-30.257-.006c4.974-6.559 10.069-12.652 15.192-18.18ZM82.802 87.83a323.167 323.167 0 0 0-7.227 13.238c-3.184-7.553-5.909-14.98-8.134-22.152c7.304-1.634 15.093-2.97 23.209-3.984a321.524 321.524 0 0 0-7.848 12.897Zm8.081 65.352c-8.385-.936-16.291-2.203-23.593-3.793c2.26-7.3 5.045-14.885 8.298-22.6a321.187 321.187 0 0 0 7.257 13.246c2.594 4.48 5.28 8.868 8.038 13.147Zm37.542 31.03c-5.184-5.592-10.354-11.779-15.403-18.433c4.902.192 9.899.29 14.978.29c5.218 0 10.376-.117 15.453-.343c-4.985 6.774-10.018 12.97-15.028 18.486Zm52.198-57.817c3.422 7.8 6.306 15.345 8.596 22.52c-7.422 1.694-15.436 3.058-23.88 4.071a382.417 382.417 0 0 0 7.859-13.026a347.403 347.403 0 0 0 7.425-13.565Zm-16.898 8.101a358.557 358.557 0 0 1-12.281 19.815a329.4 329.4 0 0 1-23.444.823c-7.967 0-15.716-.248-23.178-.732a310.202 310.202 0 0 1-12.513-19.846h.001a307.41 307.41 0 0 1-10.923-20.627a310.278 310.278 0 0 1 10.89-20.637l-.001.001a307.318 307.318 0 0 1 12.413-19.761c7.613-.576 15.42-.876 23.31-.876H128c7.926 0 15.743.303 23.354.883a329.357 329.357 0 0 1 12.335 19.695a358.489 358.489 0 0 1 11.036 20.54a329.472 329.472 0 0 1-11 20.722Zm22.56-122.124c8.572 4.944 11.906 24.881 6.52 51.026c-.344 1.668-.73 3.367-1.15 5.09c-10.622-2.452-22.155-4.275-34.23-5.408c-7.034-10.017-14.323-19.124-21.64-27.008a160.789 160.789 0 0 1 5.888-5.4c18.9-16.447 36.564-22.941 44.612-18.3ZM128 90.808c12.625 0 22.86 10.235 22.86 22.86s-10.235 22.86-22.86 22.86s-22.86-10.235-22.86-22.86s10.235-22.86 22.86-22.86Z"></path></svg>

Before

Width:  |  Height:  |  Size: 4 KiB

View file

@ -4,6 +4,7 @@ import { AlwaysOnMicrophone } from "./AlwaysOnMicrophone";
import { PushToTalk } from "./PushToTalk";
import { AudioFeedback } from "./AudioFeedback";
import { OutputDeviceSelector } from "./OutputDeviceSelector";
import { ShowOverlay } from "./ShowOverlay";
import { HandyShortcut } from "./HandyShortcut";
import { TranslateToEnglish } from "./TranslateToEnglish";
import { LanguageSelector } from "./LanguageSelector";
@ -22,6 +23,7 @@ export const Settings: React.FC = () => {
<PushToTalk descriptionMode="tooltip" grouped={true} />
<AudioFeedback descriptionMode="tooltip" grouped={true} />
<OutputDeviceSelector descriptionMode="tooltip" grouped={true} />
<ShowOverlay descriptionMode="tooltip" grouped={true} />
<TranslateToEnglish descriptionMode="tooltip" grouped={true} />
<AlwaysOnMicrophone descriptionMode="tooltip" grouped={true} />
</SettingsGroup>

View file

@ -0,0 +1,29 @@
import React from "react";
import { ToggleSwitch } from "../ui/ToggleSwitch";
import { useSettings } from "../../hooks/useSettings";
interface ShowOverlayProps {
descriptionMode?: "inline" | "tooltip";
grouped?: boolean;
}
export const ShowOverlay: React.FC<ShowOverlayProps> = ({
descriptionMode = "tooltip",
grouped = false,
}) => {
const { getSetting, updateSetting, isUpdating } = useSettings();
const showOverlayEnabled = getSetting("show_overlay") ?? true;
return (
<ToggleSwitch
checked={showOverlayEnabled}
onChange={(enabled) => updateSetting("show_overlay", enabled)}
isUpdating={isUpdating("show_overlay")}
label="Show Overlay"
description="Display visual feedback overlay during recording and transcription"
descriptionMode={descriptionMode}
grouped={grouped}
/>
);
};

View file

@ -4,5 +4,6 @@ export { OutputDeviceSelector } from "./OutputDeviceSelector";
export { AlwaysOnMicrophone } from "./AlwaysOnMicrophone";
export { PushToTalk } from "./PushToTalk";
export { AudioFeedback } from "./AudioFeedback";
export { ShowOverlay } from "./ShowOverlay";
export { HandyShortcut } from "./HandyShortcut";
export { TranslateToEnglish } from "./TranslateToEnglish";

View file

@ -199,6 +199,9 @@ export const useSettings = (): UseSettingsReturn => {
language: value,
});
break;
case "show_overlay":
await invoke("change_show_overlay_setting", { enabled: value });
break;
case "bindings":
// Handle bindings separately - they use their own invoke methods
break;
@ -243,6 +246,7 @@ export const useSettings = (): UseSettingsReturn => {
selected_output_device: "Default",
translate_to_english: false,
selected_language: "auto",
show_overlay: true,
};
const defaultValue = defaults[key];

View file

@ -29,6 +29,7 @@ export const SettingsSchema = z.object({
selected_output_device: z.string().nullable().optional(),
translate_to_english: z.boolean(),
selected_language: z.string(),
show_overlay: z.boolean(),
});
export const BindingResponseSchema = z.object({

View file

@ -0,0 +1,55 @@
.recording-overlay {
height: 40px;
/*width: min-content;*/
width: 120px;
display: flex;
gap: 12px;
align-items: center;
padding-left: 6px;
padding-right: 24px;
background: rgba(0, 0, 0, 0.6);
border-radius: 24px;
opacity: 0;
transition: opacity 300ms ease-out;
}
.bars-container {
display: flex;
align-items: end;
justify-content: center;
gap: 3px;
padding-bottom: 0px;
height: 28px;
}
.bar {
width: 6px;
background: linear-gradient(to top, #faa2ca, #f28cbb);
max-height: 28px;
border-radius: 4px;
transition: height 80ms linear;
min-height: 4px;
}
.recording-overlay.fade-in {
opacity: 1;
}
.transcribing-text {
color: #faa2ca;
font-size: 12px;
font-weight: 600;
font-family:
-apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
animation: transcribing-pulse 1.5s infinite ease-in-out;
}
@keyframes transcribing-pulse {
0%,
100% {
opacity: 0.6;
}
50% {
opacity: 1;
}
}

View file

@ -0,0 +1,94 @@
import React, { useEffect, useState, useRef } from "react";
import "./RecordingOverlay.css";
import { listen } from "@tauri-apps/api/event";
type OverlayState = "recording" | "transcribing";
const RecordingOverlay: React.FC = () => {
const [isVisible, setIsVisible] = useState(false);
const [state, setState] = useState<OverlayState>("recording");
const [levels, setLevels] = useState<number[]>(Array(16).fill(0));
const smoothedLevelsRef = useRef<number[]>(Array(16).fill(0));
useEffect(() => {
const setupEventListeners = async () => {
// Listen for show-overlay event from Rust
const unlistenShow = await listen("show-overlay", (event) => {
const overlayState = event.payload as OverlayState;
setState(overlayState);
setIsVisible(true);
});
// Listen for hide-overlay event from Rust
const unlistenHide = await listen("hide-overlay", () => {
setIsVisible(false);
});
// Listen for mic-level updates
const unlistenLevel = await listen<number[]>("mic-level", (event) => {
const newLevels = event.payload as number[];
// Apply smoothing to reduce jitter
const smoothed = smoothedLevelsRef.current.map((prev, i) => {
const target = newLevels[i] || 0;
return prev * 0.7 + target * 0.3; // Smooth transition
});
smoothedLevelsRef.current = smoothed;
console.log(smoothed.length);
setLevels(smoothed.slice(0, 10));
});
// Cleanup function
return () => {
unlistenShow();
unlistenHide();
unlistenLevel();
};
};
setupEventListeners();
}, []);
const getIconPath = () => {
return state === "recording"
? "/icon/recording.png"
: "/icon/transcribing.png";
};
const getIconAlt = () => {
return state === "recording" ? "Recording Icon" : "Transcribing Icon";
};
return (
<div className={`recording-overlay ${isVisible ? "fade-in" : ""}`}>
<img
width="28"
height="28"
src={getIconPath()}
alt={getIconAlt()}
style={{}}
/>
{state === "recording" && (
<div className="bars-container">
{levels.map((v, i) => (
<div
key={i}
className="bar"
style={{
height: `${4 + Math.pow(v, 0.7) * 32}px`, // Slight curve for better visual
transition: "height 60ms ease-out",
opacity: Math.max(0.4, v * 1.7), // Minimum opacity for visibility
}}
/>
))}
</div>
)}
{state === "transcribing" && (
<div className="transcribing-text">Transcribing...</div>
)}
</div>
);
};
export default RecordingOverlay;

19
src/overlay/index.html Normal file
View file

@ -0,0 +1,19 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<title>Recording Overlay</title>
<style>
html,
body {
margin: 0;
padding: 0;
background: transparent;
}
</style>
</head>
<body>
<div id="root"></div>
<script type="module" src="/src/overlay/main.tsx"></script>
</body>
</html>

9
src/overlay/main.tsx Normal file
View file

@ -0,0 +1,9 @@
import React from "react";
import ReactDOM from "react-dom/client";
import RecordingOverlay from "./RecordingOverlay";
ReactDOM.createRoot(document.getElementById("root") as HTMLElement).render(
<React.StrictMode>
<RecordingOverlay />
</React.StrictMode>,
);

View file

@ -1,14 +1,24 @@
import { defineConfig } from "vite";
import react from "@vitejs/plugin-react";
import tailwindcss from "@tailwindcss/vite";
import { resolve } from "path";
// @ts-expect-error process is a nodejs global
const host = process.env.TAURI_DEV_HOST;
// https://vitejs.dev/config/
export default defineConfig(async () => ({
plugins: [react(), tailwindcss()],
// Multiple entry points for main app and overlay
build: {
rollupOptions: {
input: {
main: resolve(__dirname, "index.html"),
overlay: resolve(__dirname, "src/overlay/index.html"),
},
},
},
// Vite options tailored for Tauri development and only applied in `tauri dev` or `tauri build`
//
// 1. prevent vite from obscuring rust errors