/* * ESPRESSIF MIT License * * Copyright (c) 2019 * * Permission is hereby granted for use on all ESPRESSIF SYSTEMS products, in which case, * it is free of charge, to any person obtaining a copy of this software and associated * documentation files (the "Software"), to deal in the Software without restriction, including * without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the Software is furnished * to do so, subject to the following conditions: * * The above copyright notice and this permission notice shall be included in all copies or * substantial portions of the Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS * FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR * COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER * IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. * */ #include "freertos/FreeRTOS.h" #include "freertos/task.h" #include "freertos/timers.h" #include #include "esp_log.h" #include "recorder_engine.h" #include "esp_audio.h" #include "audio_element.h" #include "audio_pipeline.h" #include "audio_mem.h" #include "board.h" #include "audio_common.h" #include "audio_hal.h" #include "filter_resample.h" #include "fatfs_stream.h" #include "raw_stream.h" #include "i2s_stream.h" #include "wav_decoder.h" #include "wav_encoder.h" #include "mp3_decoder.h" #include "aac_decoder.h" #include "http_stream.h" static char *TAG = "AUDIO_SETUP"; static audio_element_handle_t raw_read; static int _http_stream_event_handle(http_stream_event_msg_t *msg) { if (msg->event_id == HTTP_STREAM_RESOLVE_ALL_TRACKS) { return ESP_OK; } if (msg->event_id == HTTP_STREAM_FINISH_TRACK) { return http_stream_next_track(msg->el); } if (msg->event_id == HTTP_STREAM_FINISH_PLAYLIST) { return http_stream_restart(msg->el); } return ESP_OK; } void *setup_player(void *cb, void *ctx) { esp_audio_cfg_t cfg = DEFAULT_ESP_AUDIO_CONFIG(); audio_board_handle_t board_handle = audio_board_init(); audio_hal_ctrl_codec(board_handle->audio_hal, AUDIO_HAL_CODEC_MODE_BOTH, AUDIO_HAL_CTRL_START); cfg.vol_handle = board_handle->audio_hal; cfg.vol_set = (audio_volume_set)audio_hal_set_volume; cfg.vol_get = (audio_volume_get)audio_hal_get_volume; cfg.resample_rate = 48000; cfg.prefer_type = ESP_AUDIO_PREFER_MEM; cfg.cb_func = cb; cfg.cb_ctx = ctx; esp_audio_handle_t handle = esp_audio_create(&cfg); // Create readers and add to esp_audio fatfs_stream_cfg_t fs_reader = FATFS_STREAM_CFG_DEFAULT(); fs_reader.type = AUDIO_STREAM_READER; esp_audio_input_stream_add(handle, fatfs_stream_init(&fs_reader)); http_stream_cfg_t http_cfg = HTTP_STREAM_CFG_DEFAULT(); http_cfg.event_handle = _http_stream_event_handle; http_cfg.type = AUDIO_STREAM_READER; http_cfg.enable_playlist_parser = true; audio_element_handle_t http_stream_reader = http_stream_init(&http_cfg); esp_audio_input_stream_add(handle, http_stream_reader); http_stream_reader = http_stream_init(&http_cfg); esp_audio_input_stream_add(handle, http_stream_reader); // Add decoders and encoders to esp_audio wav_decoder_cfg_t wav_dec_cfg = DEFAULT_WAV_DECODER_CONFIG(); mp3_decoder_cfg_t mp3_dec_cfg = DEFAULT_MP3_DECODER_CONFIG(); mp3_dec_cfg.task_core = 1; aac_decoder_cfg_t aac_cfg = DEFAULT_AAC_DECODER_CONFIG(); aac_cfg.task_core = 1; esp_audio_codec_lib_add(handle, AUDIO_CODEC_TYPE_DECODER, aac_decoder_init(&aac_cfg)); esp_audio_codec_lib_add(handle, AUDIO_CODEC_TYPE_DECODER, wav_decoder_init(&wav_dec_cfg)); esp_audio_codec_lib_add(handle, AUDIO_CODEC_TYPE_DECODER, mp3_decoder_init(&mp3_dec_cfg)); audio_element_handle_t m4a_dec_cfg = aac_decoder_init(&aac_cfg); audio_element_set_tag(m4a_dec_cfg, "m4a"); esp_audio_codec_lib_add(handle, AUDIO_CODEC_TYPE_DECODER, m4a_dec_cfg); audio_element_handle_t ts_dec_cfg = aac_decoder_init(&aac_cfg); audio_element_set_tag(ts_dec_cfg, "ts"); esp_audio_codec_lib_add(handle, AUDIO_CODEC_TYPE_DECODER, ts_dec_cfg); // Create writers and add to esp_audio i2s_stream_cfg_t i2s_writer = I2S_STREAM_CFG_DEFAULT(); i2s_writer.type = AUDIO_STREAM_WRITER; i2s_writer.i2s_config.sample_rate = 48000; esp_audio_output_stream_add(handle, i2s_stream_init(&i2s_writer)); // Set default volume esp_audio_vol_set(handle, 60); AUDIO_MEM_SHOW(TAG); ESP_LOGI(TAG, "esp_audio instance is:%p", handle); return handle; } static esp_err_t recorder_pipeline_open(void **handle) { audio_element_handle_t i2s_stream_reader; audio_pipeline_handle_t recorder; audio_pipeline_cfg_t pipeline_cfg = DEFAULT_AUDIO_PIPELINE_CONFIG(); recorder = audio_pipeline_init(&pipeline_cfg); if (NULL == recorder) { return ESP_FAIL; } #ifdef CONFIG_ESP_LYRAT_MINI_V1_1_BOARD i2s_stream_cfg_t i2s_cfg = I2S_STREAM_CFG_DEFAULT(); i2s_cfg.i2s_port = 1; i2s_cfg.i2s_config.use_apll = 0; i2s_cfg.i2s_config.sample_rate = 16000; i2s_cfg.i2s_config.channel_format = I2S_CHANNEL_FMT_ONLY_RIGHT; i2s_cfg.type = AUDIO_STREAM_READER; i2s_stream_reader = i2s_stream_init(&i2s_cfg); #else i2s_stream_cfg_t i2s_cfg = I2S_STREAM_CFG_DEFAULT(); i2s_cfg.type = AUDIO_STREAM_READER; i2s_stream_reader = i2s_stream_init(&i2s_cfg); audio_element_info_t i2s_info = {0}; audio_element_getinfo(i2s_stream_reader, &i2s_info); i2s_info.bits = 16; i2s_info.channels = 2; i2s_info.sample_rates = 48000; audio_element_setinfo(i2s_stream_reader, &i2s_info); rsp_filter_cfg_t rsp_cfg = DEFAULT_RESAMPLE_FILTER_CONFIG(); rsp_cfg.src_rate = 48000; rsp_cfg.src_ch = 2; rsp_cfg.dest_rate = 16000; rsp_cfg.dest_ch = 1; audio_element_handle_t filter = rsp_filter_init(&rsp_cfg); #endif raw_stream_cfg_t raw_cfg = RAW_STREAM_CFG_DEFAULT(); raw_cfg.type = AUDIO_STREAM_READER; raw_read = raw_stream_init(&raw_cfg); audio_pipeline_register(recorder, i2s_stream_reader, "i2s"); audio_pipeline_register(recorder, raw_read, "raw"); #ifdef CONFIG_ESP_LYRAT_MINI_V1_1_BOARD const char *link_tag[2] = {"i2s", "raw"}; audio_pipeline_link(recorder, &link_tag[0], 2); #else audio_pipeline_register(recorder, filter, "filter"); const char *link_tag[3] = {"i2s", "filter", "raw"}; audio_pipeline_link(recorder, &link_tag[0], 3); #endif audio_pipeline_run(recorder); ESP_LOGI(TAG, "Recorder has been created"); *handle = recorder; return ESP_OK; } static esp_err_t recorder_pipeline_read(void *handle, char *data, int data_size) { raw_stream_read(raw_read, data, data_size); return ESP_OK; } static esp_err_t recorder_pipeline_close(void *handle) { audio_pipeline_deinit(handle); return ESP_OK; } void setup_recorder(rec_callback cb, void *ctx) { rec_config_t eng = DEFAULT_REC_ENGINE_CONFIG(); eng.vad_off_delay_ms = 800; eng.wakeup_time_ms = 10 * 1000; eng.evt_cb = cb; eng.open = recorder_pipeline_open; eng.close = recorder_pipeline_close; eng.fetch = recorder_pipeline_read; eng.extension = NULL; eng.support_encoding = false; eng.user_data = ctx; rec_engine_create(&eng); }