Skip to content

interrupt speech with button click #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
RomanLut wants to merge 2 commits into
base: main
Choose a base branch
from
Open

interrupt speech with button click #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
00c8c41
stop instruction
RomanLut Jun 5, 2025
281823b
disabled switching listening mode on client side
RomanLut Jun 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions firmware-arduino/src/Audio.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,8 @@ StreamCopy pitchCopier(volumePitch, queue);
AudioInfo info(SAMPLE_RATE, CHANNELS, BITS_PER_SAMPLE);
volatile bool i2sOutputFlushScheduled = false;

volatile bool talkInterruptScheduled = false;

unsigned long getSpeakingDuration() {
if (deviceState == SPEAKING && speakingStartTime > 0) {
return millis() - speakingStartTime;
Expand Down Expand Up @@ -239,6 +241,14 @@ void micTask(void *parameter) {
// Use smaller chunk size to avoid blocking too long
micToWsCopier.copyBytes(MIC_COPY_SIZE);

if ( talkInterruptScheduled == true ) {
talkInterruptScheduled = false;
const char* msg = "{\"type\": \"instruction\", \"msg\": \"INTERRUPT\", \"audio_end_ms\": 1000}";
xSemaphoreTake(wsMutex, portMAX_DELAY);
webSocket.sendTXT(msg, strlen(msg));
xSemaphoreGive(wsMutex);
}

// Yield more frequently
vTaskDelay(1);
} else {
Expand Down
2 changes: 2 additions & 0 deletions firmware-arduino/src/Audio.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,8 @@ extern I2SStream i2sInput;
extern StreamCopy micToWsCopier;
extern volatile bool i2sInputFlushScheduled;

extern volatile bool talkInterruptScheduled;

// WEBSOCKET
void webSocketEvent(WStype_t type, uint8_t *payload, size_t length);
void websocketSetup(String server_domain, int port, String path);
Expand Down
10 changes: 9 additions & 1 deletion firmware-arduino/src/main.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,6 +100,14 @@ static void onButtonDoubleClickCb(void *button_handle, void *usr_data)
enterSleep();
}

static void onButtonSingleClickCb(void *button_handle, void *usr_data)
{
Serial.println("Button single click");
// scheduleListeningRestart = true;
// scheduledTime = millis();
talkInterruptScheduled = true;
}

void getAuthTokenFromNVS()
{
preferences.begin("auth", false);
Expand Down Expand Up @@ -197,7 +205,7 @@ void setup()
Button *btn = new Button(BUTTON_PIN, false);
btn->attachLongPressUpEventCb(&onButtonLongPressUpEventCb, NULL);
btn->attachDoubleClickEventCb(&onButtonDoubleClickCb, NULL);
btn->detachSingleClickEvent();
btn->attachSingleClickEventCb(&onButtonSingleClickCb, NULL);
#endif

// Pin audio tasks to Core 1 (application core)
Expand Down
5 changes: 5 additions & 0 deletions server-deno/main.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -333,6 +333,11 @@ wss.on("connection", async (ws: WSWebSocket, payload: IPayload) => {
console.log("interrupt detected", message);
const audioEndMs = message.audio_end_ms;

client.realtime.send("response.cancel", {
type: "response.cancel",
event_id: RealtimeUtils.generateId("evt_")
});

client.realtime.send("conversation.item.truncate", {
event_id: RealtimeUtils.generateId("evt_"), // Generate unique ID
type: "conversation.item.truncate",
Expand Down