Step 7.4: HLS audio on AES67 (44.1 -> 48 kHz into the ring)

- decoder: s16 PCM -> stereo int32 -> esp_ae_rate_cvt 44.1 -> 48 kHz
  (32-bit, complexity 3; bypassed at 48 kHz; mono duplicated) -> ring.
  esp_audio_effects pinned to ~1.3.0 (1.4+ needs P4 rev >= 3).
- hls: each segment is downloaded completely into PSRAM (max 4 MB), then
  decoded; the connection is not held open while the decoder waits for
  ring space at playback speed.
- player: player_write() blocks while the ring is full and gives up when
  the source changes; the temporary 440 Hz producer is removed.
- Verified with Triple J Hottest: 441344 -> 480375 frames (10.008 s) and
  440320 -> 479260 (9.985 s) per segment; RTP 15000 packets, 0 gaps,
  peak -10 dBFS / RMS -22 dBFS; ring ~4.0 s, 0 underruns over ~50 s;
  heap 422 KB, PSRAM 27.5 MB free.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

dependencies.lock

@@ -9,6 +9,24 @@ dependencies:
       registry_url: https://components.espressif.com/
       type: service
     version: 2.5.0
+  espressif/esp_audio_effects:
+    component_hash: 6ad72ee106e25b07c9ae5b8ec77b566ef8d697473095f1c982e13247005b9ba6
+    dependencies:
+    - name: espressif/gmf_fft
+      registry_url: https://components.espressif.com
+      require: private
+      version: ~1.0
+    source:
+      registry_url: https://components.espressif.com/
+      type: service
+    version: 1.3.0~1
+  espressif/gmf_fft:
+    component_hash: b59451ef2f96d22b80c27a162515b21f1b85954dda434c0b092172164028779d
+    dependencies: []
+    source:
+      registry_url: https://components.espressif.com
+      type: service
+    version: 1.0.0
   espressif/mdns:
     component_hash: b679eafd0acae2066e2645bd91d073e33ca5be515e2545cd3c4e55a3e3bce3cb
     dependencies:
@@ -25,7 +43,8 @@ dependencies:
     version: 5.5.5
 direct_dependencies:
 - espressif/esp_audio_codec
+- espressif/esp_audio_effects
 - espressif/mdns
-manifest_hash: e85f2bff1cc890def1a35e7da5210473c09ec845364a2bc2e54f6d2a7de54cbc
+manifest_hash: 95404bd3492778da35a8aeee53935ee8ad13b09c56ae5fcbe77a4e921dafbb23
 target: esp32p4
 version: 2.0.0

main/decoder.c

@@ -6,11 +6,21 @@
 #include "esp_audio_dec_default.h"
 #include "esp_audio_simple_dec.h"
 #include "esp_audio_simple_dec_default.h"
+#include "esp_ae_rate_cvt.h"
+#include "player.h"
 #include "esp_heap_caps.h"
 #include "esp_log.h"
 
 static const char *TAG = "decoder";
 
+#define OUT_RATE        48000
+#define CONV_FRAMES     4096            // per rate converter call
+
+static esp_ae_rate_cvt_handle_t s_cvt;  // NULL: no conversion (source is 48 kHz)
+static uint32_t s_cvt_rate;             // input rate the converter was opened for
+static int32_t *s_in32, *s_out32;       // stereo int32 work buffers (PSRAM)
+static uint64_t s_seg_out;              // 48 kHz frames written this segment
+
 static esp_audio_simple_dec_handle_t s_dec;
 static uint8_t *s_pcm;
 static uint32_t s_pcm_size = 8192;
@@ -25,15 +35,61 @@ static int s_pmt_pid = -1, s_audio_pid = -1;
 static void report_segment(void)
 {
     if (s_seg_count && s_info.sample_rate) {
-        ESP_LOGI(TAG, "segment: %llu ES bytes -> %llu PCM frames = %.3f s (%lu Hz, %u ch, %u bit)",
+        ESP_LOGI(TAG, "segment: %llu ES bytes -> %llu frames at %lu Hz = %.3f s -> %llu frames at 48 kHz = %.3f s",
-                 s_seg_es, s_seg_frames, (double)s_seg_frames / s_info.sample_rate,
+                 s_seg_es, s_seg_frames, (unsigned long)s_info.sample_rate,
-                 (unsigned long)s_info.sample_rate, s_info.channel, s_info.bits_per_sample);
+                 (double)s_seg_frames / s_info.sample_rate, s_seg_out, (double)s_seg_out / OUT_RATE);
     }
     s_seg_frames = 0;
     s_seg_es = 0;
+    s_seg_out = 0;
     s_seg_count++;
 }
 
+// Decoded PCM (s16, any channel count) -> stereo int32 -> 48 kHz -> ring.
+static void output_pcm(const int16_t *pcm, uint32_t frames)
+{
+    int ch = s_info.channel;
+    if (s_info.sample_rate != s_cvt_rate) {
+        if (s_cvt) {
+            esp_ae_rate_cvt_close(s_cvt);
+            s_cvt = NULL;
+        }
+        s_cvt_rate = s_info.sample_rate;
+        if (s_cvt_rate != OUT_RATE) {
+            esp_ae_rate_cvt_cfg_t cfg = {
+                .src_rate = s_cvt_rate, .dest_rate = OUT_RATE, .channel = 2, .bits_per_sample = 32,
+                .complexity = 3, .perf_type = ESP_AE_RATE_CVT_PERF_TYPE_SPEED,
+            };
+            if (esp_ae_rate_cvt_open(&cfg, &s_cvt) != ESP_AE_ERR_OK) {
+                ESP_LOGE(TAG, "rate converter %lu -> %d Hz: open failed", (unsigned long)s_cvt_rate, OUT_RATE);
+            } else {
+                ESP_LOGI(TAG, "rate converter %lu -> %d Hz", (unsigned long)s_cvt_rate, OUT_RATE);
+            }
+        }
+    }
+    while (frames) {
+        uint32_t n = frames < CONV_FRAMES ? frames : CONV_FRAMES;
+        for (uint32_t i = 0; i < n; i++) {      // to stereo int32 (full scale = INT32_MAX)
+            int32_t l = (int32_t)pcm[i * ch] << 16;
+            s_in32[i * 2] = l;
+            s_in32[i * 2 + 1] = ch > 1 ? (int32_t)pcm[i * ch + 1] << 16 : l;
+        }
+        const int32_t *out = s_in32;
+        uint32_t out_n = n;
+        if (s_cvt) {
+            out_n = CONV_FRAMES * 2;
+            if (esp_ae_rate_cvt_process(s_cvt, s_in32, n, s_out32, &out_n) != ESP_AE_ERR_OK) {
+                ESP_LOGW(TAG, "rate conversion failed");
+                return;
+            }
+            out = s_out32;
+        }
+        s_seg_out += player_write(out, out_n);
+        pcm += n * ch;
+        frames -= n;
+    }
+}
+
 // Feed ADTS-AAC elementary stream bytes to the decoder.
 static void decode_es(const uint8_t *data, size_t len)
 {
@@ -62,7 +118,11 @@ static void decode_es(const uint8_t *data, size_t len)
                 ESP_LOGI(TAG, "stream: %lu Hz, %u ch, %u bit, %lu bit/s", (unsigned long)s_info.sample_rate,
                          s_info.channel, s_info.bits_per_sample, (unsigned long)s_info.bitrate);
             }
-            s_seg_frames += out.decoded_size / (s_info.channel * s_info.bits_per_sample / 8);
+            uint32_t n = out.decoded_size / (s_info.channel * s_info.bits_per_sample / 8);
+            s_seg_frames += n;
+            if (s_info.bits_per_sample == 16) {
+                output_pcm((const int16_t *)out.buffer, n);
+            }
         }
         raw.buffer += raw.consumed;
         raw.len -= raw.consumed;
@@ -168,5 +228,7 @@ esp_err_t decoder_init(void)
         return ESP_FAIL;
     }
     s_pcm = heap_caps_malloc(s_pcm_size, MALLOC_CAP_SPIRAM);
-    return s_pcm ? ESP_OK : ESP_ERR_NO_MEM;
+    s_in32 = heap_caps_malloc(CONV_FRAMES * 2 * sizeof(int32_t), MALLOC_CAP_SPIRAM);
+    s_out32 = heap_caps_malloc(CONV_FRAMES * 2 * 2 * sizeof(int32_t), MALLOC_CAP_SPIRAM);
+    return s_pcm && s_in32 && s_out32 ? ESP_OK : ESP_ERR_NO_MEM;
 }

main/hls.c

@@ -19,6 +19,7 @@
 #define LIVE_BACK       3           // start this many segments behind the live edge
 #define CHUNK           4096
 #define MAX_REDIRECTS   5
+#define SEG_MAX         (4 * 1024 * 1024)   // largest segment we accept (PSRAM)
 
 static const char *TAG = "hls";
 
@@ -34,6 +35,7 @@ static char *s_text;                // playlist buffer (PSRAM)
 static media_pl_t *s_pl;            // parsed media playlist (PSRAM)
 static char s_url[URL_MAX];         // configured URL
 static char s_media_url[URL_MAX];
+static uint8_t *s_seg;              // current segment (PSRAM)
 
 // hls_url when source.mode needs HLS, else "".
 static void wanted_url(char *out, size_t n)
@@ -209,30 +211,25 @@ static bool fetch_segment(long long seq, const char *url)
     if (!c) {
         return false;
     }
-    static uint8_t buf[CHUNK];
+    // Download completely first, then decode: the connection is not held open while the
+    // decoder waits for space in the ring (a stalled TCP stream for ~10 s may get cut by the CDN).
     size_t total = 0;
-    int r;
+    int r = 0;
-    bool ok = true, first = true;
+    bool ok = true;
-    while ((r = esp_http_client_read(c, (char *)buf, sizeof(buf))) > 0) {
+    while (total < SEG_MAX && (r = esp_http_client_read(c, (char *)s_seg + total, SEG_MAX - total)) > 0) {
-        if (s_sink && !s_sink(buf, r, first)) {
-            ok = false;
-            break;
-        }
-        first = false;
         total += r;
-        if (!still_wanted()) {
-            ok = false;
-            break;
-        }
     }
-    if (r < 0) {
+    if (r < 0 || total == SEG_MAX) {
         ok = false;
     }
     esp_http_client_close(c);
     esp_http_client_cleanup(c);
     int64_t us = esp_timer_get_time() - t0;
-    ESP_LOGI(TAG, "segment %lld: %u bytes in %.2f s (%.1f Mbit/s)%s", seq, (unsigned)total, us / 1e6,
+    ESP_LOGD(TAG, "segment %lld: %u bytes in %.2f s (%.1f Mbit/s)%s", seq, (unsigned)total, us / 1e6,
-             us ? total * 8.0 / us : 0.0, ok ? "" : ", aborted");
+             us ? total * 8.0 / us : 0.0, ok ? "" : ", failed");
+    if (ok && s_sink) {
+        ok = s_sink(s_seg, total, true);   // blocks at playback speed while the ring is full
+    }
     return ok;
 }
 
@@ -300,7 +297,8 @@ esp_err_t hls_start(hls_sink_t sink)
     s_sink = sink;
     s_text = heap_caps_malloc(PLAYLIST_MAX, MALLOC_CAP_SPIRAM);
     s_pl = heap_caps_malloc(sizeof(media_pl_t), MALLOC_CAP_SPIRAM);
-    if (!s_text || !s_pl) {
+    s_seg = heap_caps_malloc(SEG_MAX, MALLOC_CAP_SPIRAM);
+    if (!s_text || !s_pl || !s_seg) {
         return ESP_ERR_NO_MEM;
     }
     return xTaskCreate(hls_task, "hls", 10240, NULL, 4, NULL) == pdPASS ? ESP_OK : ESP_ERR_NO_MEM;

main/idf_component.yml

@@ -1,3 +1,4 @@
 dependencies:
-  # 2.6+ uses P4 assembly that needs chip rev >= 3.0; this board is rev 1.3 (see CLAUDE.md).
+  # Newer versions use P4 assembly that needs chip rev >= 3.0; this board is rev 1.3 (see CLAUDE.md).
   espressif/esp_audio_codec: "~2.5.0"
+  espressif/esp_audio_effects: "~1.3.0"

main/player.c

@@ -1,6 +1,5 @@
 #include "player.h"
 
-#include <math.h>
 #include <string.h>
 
 #include "aes67_cfg.h"
@@ -72,24 +71,22 @@ void player_apply(const cJSON *source)
     ESP_LOGI(TAG, "source: %s", SRC_NAME[src]);
 }
 
-/* ----- Step 7.1: temporary test producer (440 Hz into the ring), replaced by the HLS player ----- */
+// Source side (HLS task): write converted 48 kHz frames, waiting for space at playback speed.
-
+// Gives up when the source is no longer HLS.
-static void test_producer(void *arg)
+size_t player_write(const int32_t *frames, size_t n)
 {
-    static int32_t chunk[480 * CHANNELS];
+    size_t done = 0;
-    uint32_t phase = 0;
+    while (done < n) {
-    const double amp = pow(10.0, -18.0 / 20.0) * 2147483647.0;
+        if (s_src != SRC_HLS) {
-    while (1) {
+            return done;
-        if (s_src != SRC_HLS || audio_ring_space() < 480) {
-            vTaskDelay(pdMS_TO_TICKS(10));
-            continue;
         }
-        for (int i = 0; i < 480; i++, phase++) {
+        size_t w = audio_ring_write(frames + done * CHANNELS, n - done);
-            int32_t v = (int32_t)(amp * sin(2.0 * M_PI * 440.0 * (phase % RATE) / RATE));
+        if (!w) {
-            chunk[i * 2] = chunk[i * 2 + 1] = v;
+            vTaskDelay(pdMS_TO_TICKS(20));
         }
-        audio_ring_write(chunk, 480);
+        done += w;
     }
+    return done;
 }
 
 static void player_status(cJSON *st)
@@ -113,12 +110,11 @@ esp_err_t player_init(void)
     s_src = (src_t)-1;
     player_apply(src);
     cJSON_Delete(src);
-    xTaskCreate(test_producer, "test_prod", 3072, NULL, 5, NULL);
     err = decoder_init();
     if (err != ESP_OK) {
         return err;
     }
-    err = hls_start(decoder_feed);  // 7.3: decode and log; resampling + ring in 7.4
+    err = hls_start(decoder_feed);
     if (err != ESP_OK) {
         return err;
     }

main/player.h

@@ -1,9 +1,14 @@
 // Project player: picks the audio source for AES67 TX (test tone, silence, HLS, Spotify).
 #pragma once
 
+#include <stddef.h>
+#include <stdint.h>
+
 #include "cJSON.h"
 #include "esp_err.h"
 
 esp_err_t player_init(void);
 // Apply the "source" config group (mode etc.).
 void player_apply(const cJSON *source);
+// Source side: write 48 kHz stereo int32 frames, blocking while the ring is full.
+size_t player_write(const int32_t *frames, size_t n);