Add sendspin functionality for Sonocottas ESP32 hifi

2025-12-19 17:30:35 +01:00
parent 2e17dadd27
commit bb15cbe280
3 changed files with 378 additions and 0 deletions
--- a/esphome/sonocotta/esp32-hifi/esp32-sendspin-beta.yaml
+++ b/esphome/sonocotta/esp32-hifi/esp32-sendspin-beta.yaml
@@ -0,0 +1,174 @@
+# SPDX-License-Identifier: Apache-2.0
+#
+# This file incorporates and is derived from material originally licensed under:
+# - Apache License, Version 2.0
+# - MIT License
+#
+# The combined and modified work is licensed under the Apache License, Version 2.0.
+# See the LICENSE file in the repository root for full license text.
+
+# This is based on a mix of
+# - https://github.com/esphome/home-assistant-voice-pe/blob/b2cf3e52a9fd3a701d2ff917c296e8ef9032d14e/home-assistant-voice.yaml (MIT license)
+# - https://github.com/sonocotta/esp32-audio-dock/blob/8f39d54b785ee3403ddc8afa4e12c99eb69c9e6a/firmware/esphome/hifi-esp32-idf.yaml (Apache 2.0 License)
+
+
+external_components:
+  - source:
+      # https://github.com/esphome/esphome/pull/12253
+      type: git
+      url: https://github.com/esphome/esphome
+      ref: 0fe230114c80b6d3378f04c777baadee178e40ad
+    components: [mixer]
+  - source:
+      # https://github.com/esphome/esphome/pull/12254
+      type: git
+      url: https://github.com/esphome/esphome
+      ref: 1ab4b990092ae063a16cb1511a188c536fdb336e
+    components: [resampler]
+  - source:
+      # https://github.com/esphome/esphome/pull/12256
+      type: git
+      url: https://github.com/esphome/esphome
+      ref: 047ba60f01af84513f8d5aabaa2a53074facee8f
+    components: [audio]
+  - source:
+      # https://github.com/esphome/esphome/pull/12258
+      type: git
+      url: https://github.com/esphome/esphome
+      ref: bff22983a390352360796f8e1363127e0cd1f898
+    components: [media_player]
+  - source:
+      # https://github.com/esphome/esphome/pull/12284
+      type: git
+      url: https://github.com/esphome/esphome
+      ref: 9d2d2f6287a72af6397dfd93ee56fbab25c1d32f
+    components: [mdns, sendspin]
+  - source:
+      # https://github.com/esphome/esphome/pull/12429
+      type: git
+      url: https://github.com/esphome/esphome
+      ref: 72499eaed2ed54316aca90d368053aa2e1a54f5f
+    refresh: 0s
+    components: [file, http_request, media_source, speaker_source]
+
+esphome:
+  name: test-player
+  friendly_name: test-player
+  min_version: 2025.12.0
+
+esp32:
+  board: mhetesp32minikit
+  flash_size: 8MB
+  framework:
+    type: esp-idf
+    version: recommended
+    sdkconfig_options:
+      CONFIG_BT_ALLOCATION_FROM_SPIRAM_FIRST: "y"
+      CONFIG_BT_BLE_DYNAMIC_ENV_MEMORY: "y"
+
+      CONFIG_MBEDTLS_EXTERNAL_MEM_ALLOC: "y"
+      CONFIG_MBEDTLS_SSL_PROTO_TLS1_3: "y"  # TLS1.3 support isn't enabled by default in IDF 5.1.5
+
+# Enable logging
+logger:
+
+# Enable Home Assistant API
+api:
+  encryption:
+    key: "keykeykey"
+
+ota:
+  - platform: esphome
+    password: "keykeykey"
+
+wifi:
+  ssid: !secret wifi_ssid
+  password: !secret wifi_password
+
+  # Enable fallback hotspot (captive portal) in case wifi connection fails
+  ap:
+    ssid: "Test-Player Fallback Hotspot"
+    password: !secret ap_fallback
+
+captive_portal:
+    
+psram:
+  speed: 80MHz
+
+i2s_audio:
+  i2s_lrclk_pin: GPIO25
+  i2s_bclk_pin: GPIO26
+
+speaker:
+  - platform: i2s_audio
+    id: speaker_id
+    dac_type: external
+    i2s_dout_pin: GPIO22
+    channel: stereo
+    sample_rate: 48000
+    timeout: never
+      # Virtual speakers to combine the announcement and media streams together into one output
+  - platform: mixer
+    id: mixing_speaker
+    output_speaker: speaker_id
+    num_channels: 2
+    task_stack_in_psram: False
+    source_speakers:
+      - id: announcement_mixing_input
+        timeout: never
+      - id: media_mixing_input
+        timeout: never
+
+  # Virtual speakers to resample each pipelines' audio, if necessary, as the mixer speaker requires the same sample rate
+  - platform: resampler
+    id: announcement_resampling_speaker
+    output_speaker: announcement_mixing_input
+    sample_rate: 48000
+    bits_per_sample: 16
+  - platform: resampler
+    id: media_resampling_speaker
+    output_speaker: media_mixing_input
+    sample_rate: 48000
+    bits_per_sample: 16
+
+
+sendspin:
+  id: sendspin_hub
+  task_stack_in_psram: false
+  kalman_process_error: 0.01
+
+media_source:
+  - platform: sendspin
+    id: sendspin_source
+#  - platform: http_request
+#    id: http_source
+#    buffer_size: 500000
+
+media_player:
+  - platform: sendspin
+    id: sendspin_group_media_player
+  - platform: speaker_source
+    id: external_media_player
+    name: Media Player
+    announcement_speaker: announcement_resampling_speaker
+    media_speaker: media_resampling_speaker
+    announcement_pipeline:
+      format: FLAC     # FLAC is the least processor intensive codec
+      num_channels: 1  # Stereo audio is unnecessary for announcements
+      sample_rate: 48000
+    media_pipeline:
+      format: FLAC     # FLAC is the least processor intensive codec
+      num_channels: 2
+      sample_rate: 48000
+    volume_increment: 0.05
+    volume_min: 0.4
+    volume_max: 0.85
+    sources:
+#      - http_source
+      - sendspin_source
+    on_announcement:
+      - mixer_speaker.apply_ducking:
+          id: media_mixing_input
+          decibel_reduction: 20
+          duration: 0.0s
+