add different sample rates for mic and speakers on 01

software/source/clients/esp32/src/client/client.ino

@@ -541,7 +541,9 @@ void tryReconnectWiFi() {
 }
 void tryReconnectToServer() {
     preferences.begin("network", true); // Open Preferences with the "network" namespace in ReadOnly mode
-    String serverURL = preferences.getString("server_url", ""); // Get stored server URL, if any
+    const String SERVER_URL="sterling-snail-conversely.ngrok-free.app";
+    String serverURL = SERVER_URL; // Get stored server URL, if any
+    // String serverURL = preferences.getString("server_url", ""); // Get stored server URL, if any
     preferences.end(); // Close the Preferences
 
     if (!serverURL.isEmpty()) {
@@ -573,6 +575,9 @@ void tryReconnectToServer() {
 
 #define MAX_DATA_LEN (1024 * 9)
 
+#define MIC_SAMPLE_RATE 16000
+#define SPEAKER_SAMPLE_RATE 24000  // or 22050 for OpenAI TTS
+
 uint8_t microphonedata0[1024 * 10];
 uint8_t speakerdata0[1024 * 1];
 int speaker_offset;
@@ -615,7 +620,6 @@ void InitI2SSpeakerOrMic(int mode)
     i2s_driver_uninstall(SPEAKER_I2S_NUMBER);
     i2s_config_t i2s_config = {
         .mode = (i2s_mode_t)(I2S_MODE_MASTER),
-        .sample_rate = 16000,
         .bits_per_sample =
             I2S_BITS_PER_SAMPLE_16BIT, // is fixed at 12bit, stereo, MSB
         .channel_format = I2S_CHANNEL_FMT_ALL_RIGHT,
@@ -633,12 +637,14 @@ void InitI2SSpeakerOrMic(int mode)
     {
         i2s_config.mode =
             (i2s_mode_t)(I2S_MODE_MASTER | I2S_MODE_RX | I2S_MODE_PDM);
+        i2s_config.sample_rate = MIC_SAMPLE_RATE;
     }
     else
     {
         i2s_config.mode = (i2s_mode_t)(I2S_MODE_MASTER | I2S_MODE_TX);
         i2s_config.use_apll = false;
         i2s_config.tx_desc_auto_clear = true;
+        i2s_config.sample_rate = SPEAKER_SAMPLE_RATE;
     }
 
     err += i2s_driver_install(SPEAKER_I2S_NUMBER, &i2s_config, 0, NULL);
@@ -652,8 +658,10 @@ void InitI2SSpeakerOrMic(int mode)
     tx_pin_config.data_out_num = CONFIG_I2S_DATA_PIN;
     tx_pin_config.data_in_num = CONFIG_I2S_DATA_IN_PIN;
     err += i2s_set_pin(SPEAKER_I2S_NUMBER, &tx_pin_config);
-    err += i2s_set_clk(SPEAKER_I2S_NUMBER, 16000, I2S_BITS_PER_SAMPLE_16BIT,
+    err += i2s_set_clk(SPEAKER_I2S_NUMBER,
-                    I2S_CHANNEL_MONO);
+                        (mode == MODE_MIC) ? MIC_SAMPLE_RATE : SPEAKER_SAMPLE_RATE,      // set the sample rate here as well
+                        I2S_BITS_PER_SAMPLE_16BIT,
+                        I2S_CHANNEL_MONO);
 }
 
 void speaker_play(uint8_t *payload, uint32_t len)
@@ -783,15 +791,18 @@ void setup() {
     Serial.setTxBufferSize(1024); // Set the transmit buffer size for the Serial object.
 
     WiFi.mode(WIFI_AP_STA); // Set WiFi mode to both AP and STA.
-
+    const String WIFI_NAME="gunner1";
+    const String WIFI_PASSWORD="startup1";
     // delay(100); // Short delay to ensure mode change takes effect
     // WiFi.softAPConfig(localIP, gatewayIP, subnetMask);
     // WiFi.softAP(ssid, password);
-    startSoftAccessPoint(ssid, password, localIP, gatewayIP);
+    // startSoftAccessPoint(ssid, password, localIP, gatewayIP);
+    connectToWifi(WIFI_NAME, WIFI_PASSWORD);
     setUpDNSServer(dnsServer, localIP);
+    tryReconnectToServer();
 
-    setUpWebserver(server, localIP);
+    // setUpWebserver(server, localIP);
-    tryReconnectWiFi();
+    // tryReconnectWiFi();
     // Print a welcome message to the Serial port.
     Serial.println("\n\nCaptive Test, V0.5.0 compiled " __DATE__ " " __TIME__ " by CD_FER");
     Serial.printf("%s-%d\n\r", ESP.getChipModel(), ESP.getChipRevision());

software/source/server/async_interpreter.py

@@ -11,7 +11,7 @@
 
 ###
 from pynput import keyboard
-
+from .utils.bytes_to_wav import bytes_to_wav
 from RealtimeTTS import TextToAudioStream, CoquiEngine, OpenAIEngine, ElevenlabsEngine
 from RealtimeSTT import AudioToTextRecorder
 import time
@@ -23,6 +23,7 @@ import os
 class AsyncInterpreter:
     def __init__(self, interpreter):
         self.interpreter = interpreter
+        self.audio_chunks = []
 
         # STT
         self.stt = AudioToTextRecorder(
@@ -73,6 +74,7 @@ class AsyncInterpreter:
         if isinstance(chunk, bytes):
             # It's probably a chunk of audio
             self.stt.feed_audio(chunk)
+            self.audio_chunks.append(chunk)
             # print("INTERPRETER FEEDING AUDIO")
 
         else:
@@ -171,6 +173,12 @@ class AsyncInterpreter:
 
         message = self.stt.text()
 
+        if self.audio_chunks:
+            audio_bytes = bytearray(b"".join(self.audio_chunks))
+            wav_file_path = bytes_to_wav(audio_bytes, "audio/raw")
+            print("wav_file_path ", wav_file_path)
+            self.audio_chunks = []
+
         print(message)
 
         # Feed generate to RealtimeTTS
@@ -181,8 +189,8 @@ class AsyncInterpreter:
         text_iterator = self.generate(message, start_interpreter)
 
         self.tts.feed(text_iterator)
-
+        if not self.tts.is_playing():
-        self.tts.play_async(on_audio_chunk=self.on_tts_chunk, muted=True)
+            self.tts.play_async(on_audio_chunk=self.on_tts_chunk, muted=True)
 
         while True:
             await asyncio.sleep(0.1)

software/source/server/profiles/default.py

@@ -5,7 +5,7 @@ from interpreter import interpreter
 
 # 01 supports OpenAI, ElevenLabs, and Coqui (Local) TTS providers
 # {OpenAI: "openai", ElevenLabs: "elevenlabs", Coqui: "coqui"}
-interpreter.tts = "elevenlabs"
+interpreter.tts = "openai"
 
 # Connect your 01 to a language model
 interpreter.llm.model = "gpt-4-turbo"