【ESP32-S3-BOX-3B】【使用VOLC RTC 语音交互例程接入火山引擎进行语音交互没有声音】 (AUD-6524) #1494
Description
使用这个https://gitee.com/EspressifSystems/esp-adf/tree/master/examples/ai_agent/volc_rtc 示例，按文档配置编译，如果使用coze 方案及默认测试账号，是可以跟设备AI对话的。当使用火山智能体时，就没有声音，不能对话，加入房间时也没有声音输出。使用浏览器“无代码跑通实时对话式 AI Demo”是可以对话的，开机日志及启动智能体请求及相应信息如下，请帮忙看看是什么原因
请求数据：
{
"query": {},
"body": {
"AppId": "686******8d3d",
"RoomId": "ChatRoom03",
"TaskId": "ChatTask03",
"Config": {
"ASRConfig": {
"Provider": "volcano",
"ProviderParams": {
"Mode": "smallmodel",
"AppId": "8640329948",
"AccessToken": "oCXibbIGXBr78xU62NJEBKuaMq7gObl5",
"ApiResourceId": "volc.bigasr.sauc.duration",
"Cluster": "volcengine_streaming_common",
"StreamMode": 0
}
},
"TTSConfig": {
"Provider": "volcano",
"ProviderParams": {
"app": {
"appid": "8640329948",
"cluster": "volcano_tts",
"token": "oCXibbIGXBr78xU62NJEBKuaMq7gObl5"
},
"audio": {
"speed_ratio": 1,
"voice_type": "BV001_streaming",
"volume_ratio": 2,
"pitch_ratio": 1,
"pitch_rate": 0,
"speech_rate": 0
}
}
},
"LLMConfig": {
"Mode": "ArkV3",
"EndPointId": "ep-20250708110436-bgvqc"
}
},
"AgentConfig": {
"TargetUserId": [
"liuxing123"
],
"WelcomeMessage": "你好呀，我是乐鑫AI助手",
"UserId": "lexin"
}
}
}
响应结果：
{
"Result": "The task has been started. Please do not call the startup task interface repeatedly.",
"ResponseMetadata": {
"RequestId": "20250709150439368CAA87789AFE039341",
"Action": "StartVoiceChat",
"Version": "2024-12-01",
"Service": "rtc",
"Region": "cn-beijing"
}
}
设备开机日志：
I (407) esp_image: segment 4: paddr=001f3fe0 vaddr=4037b090 sizeI (982) esp_psram: SPI SRAM memory test OK
I (990) cpu_start: Pro cpu start user code
I (990) cpu_start: cpu freq: 240000000 Hz
I (991) app_init: Application information:
I (991) app_init: Project name: volc_rtc
I (994) app_init: App version: v2.7-113-g1e839afb-dirty
I (1000) app_init: Compile time: Jul 9 2025 11:37:45
I (1005) app_init: ELF file SHA256: 6bb64914b...
I (1009) app_init: ESP-IDF: v5.4.1-dirty
I (1014) efuse_init: Min chip rev: v0.0
I (1018) efuse_init: Max chip rev: v0.99
I (1022) efuse_init: Chip rev: v0.2
I (1026) heap_init: Initializing. RAM available for dynamic allocation:
I (1032) heap_init: At 3FCBD2F0 len 0002C420 (177 KiB): RAM
I (1037) heap_init: At 3FCE9710 len 00005724 (21 KiB): RAM
I (1043) heap_init: At 600FE11C len 00001ECC (7 KiB): RTCRAM
I (1048) esp_psram: Adding pool of 14400K of PSRAM memory to heap allocator
I (1055) spi_flash: detected chip: gd
I (1058) spi_flash: flash io: qio
I (1061) sleep_gpio: Configure to isolate all GPIO pins in sleep state
I (1067) sleep_gpio: Enable automatic switching of GPIO sleep configuration
I (1074) main_task: Started on CPU0
I (1077) esp_psram: Reserving pool of 32K of internal memory for DMA/internal allocations
I (1085) main_task: Calling app_main()
I (1091) main: Initialize board peripherals
I (1094) PERIPH_SPIFFS: Partition size: total: 52961, used: 12299
I (1098) AUDIO_THREAD: The esp_periph task allocate stack on internal memory
I (1108) pp: pp rom version: e7ae62f
I (1108) net80211: net80211 rom version: e7ae62f
I (1114) wifi:wifi driver task: 3fcd2108, prio:23, stack:6656, core=0
I (1120) wifi:wifi firmware version: 79fa3f41ba
I (1123) wifi:wifi certification version: v7.0
I (1127) wifi:config NVS flash: enabled
I (1131) wifi:config nano formatting: disabled
I (1135) wifi:Init data frame dynamic rx buffer num: 32
I (1140) wifi:Init static rx mgmt buffer num: 5
I (1144) wifi:Init management short buffer num: 32
I (1149) wifi:Init static tx buffer num: 16
I (1153) wifi:Init tx cache buffer num: 32
I (1156) wifi:Init static tx FG buffer num: 2
I (1160) wifi:Init static rx buffer size: 1600
I (1165) wifi:Init static rx buffer num: 16
I (1168) wifi:Init dynamic rx buffer num: 32
I (1173) wifi_init: rx ba win: 16
I (1175) wifi_init: accept mbox: 6
I (1179) wifi_init: tcpip mbox: 32
I (1182) wifi_init: udp mbox: 6
I (1185) wifi_init: tcp mbox: 6
I (1187) wifi_init: tcp tx win: 5760
I (1191) wifi_init: tcp rx win: 5760
I (1194) wifi_init: tcp mss: 1440
I (1197) wifi_init: WiFi/LWIP prefer SPIRAM
I (1201) wifi_init: WiFi IRAM OP enabled
I (1205) wifi_init: WiFi RX IRAM OP enabled
W (1209) wifi:Password length matches WPA2 standards, authmode threshold changes from OPEN to WPA2
I (1217) wifi:Set ps type: 1, coexist: 0
I (1221) phy_init: phy_version 700,8582a7fd,Feb 10 2025,20:13:11
I (1262) wifi:mode : sta (b4:3a:45:0b:77:cc)
I (1263) wifi:enable tsf
W (1263) PERIPH_WIFI: WiFi Event cb, Unhandle event_base:WIFI_EVENT, event_id:43
I (2141) wifi:new:<7,0>, old:<1,0>, ap:<255,255>, sta:<7,0>, prof:1, snd_ch_cfg:0x0
I (2141) wifi:state: init -> auth (0xb0)
W (2141) PERIPH_WIFI: WiFi Event cb, Unhandle event_base:WIFI_EVENT, event_id:43
I (2145) wifi:state: auth -> assoc (0x0)
I (2156) wifi:state: assoc -> run (0x10)
I (2368) wifi:connected with liuxing_2.4G, aid = 1, channel 7, BW20, bssid = 0c:4b:54:34:53:60
I (2369) wifi:security: WPA2-PSK, phy: bg, rssi: -42
I (2370) wifi:pm start, type: 1
I (2373) wifi:dp: 1, bi: 102400, li: 3, scale listen interval from 307200 us to 307200 us
I (2381) wifi:set rx beacon pti, rx_bcn_pti: 0, bcn_timeout: 25000, mt_pti: 0, mt_time: 10000
W (2390) PERIPH_WIFI: WiFi Event cb, Unhandle event_base:WIFI_EVENT, event_id:4
I (2470) wifi:AP's beacon interval = 102400 us, DTIM period = 1
I (3413) esp_netif_handlers: sta ip: 192.168.1.103, mask: 255.255.255.0, gw: 192.168.1.1
I (3413) PERIPH_WIFI: Got ip:192.168.1.103
W (3737) i2c_bus_v2: I2C master handle is NULL, will create new one
E (3738) i2c.master: I2C transaction unexpected nack detected
E (3738) i2c.master: s_i2c_synchronous_transaction(924): I2C transaction failed
E (3745) i2c.master: i2c_master_multi_buffer_transmit(1186): I2C transaction failed
I (3757) DRV8311: ES8311 in Slave mode
I (3767) gpio: GPIO[46]| InputEn: 0| OutputEn: 1| OpenDrain: 0| Pullup: 0| Pulldown: 0| Intr:0
I (3774) ES7210: ES7210 in Slave mode
I (3782) ES7210: Enable ES7210_INPUT_MIC1
I (3785) ES7210: Enable ES7210_INPUT_MIC2
I (3788) ES7210: Enable ES7210_INPUT_MIC3
W (3791) ES7210: Enable TDM mode. ES7210_SDP_INTERFACE2_REG12: 2
I (3796) ES7210: config fmt 60
I (3798) AUDIO_HAL: Codec mode is 3, Ctrl:1
I (3804) AUDIO_PROCESSOR: Create audio pipeline for audio player
I (3804) AUDIO_PROCESSOR: Create audio player audio stream
I (3806) AUDIO_PROCESSOR: Register all elements to playback pipeline
I (3812) AUDIO_PROCESSOR: Link playback element together raw-->audio_decoder-->i2s_stream-->[codec_chip]
E (3821) gpio: gpio_install_isr_service(502): GPIO isr service already installed
I (3828) DISPATCHER: exe first list: 0x0
I (3832) DISPATCHER: dispatcher_event_task is running...
I (3837) volc_rtc: app_id: 6868d3d, room_id: liuxing, uid: liuxing123, token: 0016****qbU=
2025-07-09 15:04:44.130 [E] VolcEngineRTCLite.c:112 ****************** HELLO BOOKA (686c81ae6790700172578d3d)(1.56.002.09500)(c48915dc01ca27f5a98be735dfef3138d4beaac7) ********************Duplicate of #
2025-07-09 15:04:44.147 [E] Cache.c:270 operation returned status code: 0x00000009
I (3890) AUDIO_PROCESSOR: recorder_pipeline_open
I (3890) AUDIO_PROCESSOR: Create audio pipeline for recording
I (3894) AUDIO_PROCESSOR: Create player audio stream
I (3902) AUDIO_PROCESSOR: Register all player elements to audio pipeline
I (3905) AUDIO_PROCESSOR: Link all player elements to audio pipeline
I (3911) AUDIO_PROCESSOR: player_pipeline_open
I (3915) AUDIO_PROCESSOR: Create audio pipeline for playback
I (3921) AUDIO_PROCESSOR: Create playback audio stream
I (3925) DUAL_MICROPHONES: Create opus decoder
I (3930) AUDIO_PROCESSOR: Register all elements to playback pipeline
I (3936) AUDIO_PROCESSOR: ENBALE_AUDIO_STREAM_DUAL_MIC
I (3941) AUDIO_PROCESSOR: Link playback element together raw-->audio_decoder-->rsp-->i2s_stream-->[codec_chip]
I (3969) AUDIO_PROCESSOR: player pipe start running
I (3969) volc_rtc: start join room
2025-07-09 15:04:44.385 [E] RoomImplX.c:167 operation returned status code: 0x52000057
2025-07-09 15:04:44.705 [E] Cache.c:309 operation returned status code: 0x00000009
2025-07-09 15:04:44.708 [E] RoomImplX.c:167 operation returned status code: 0x52000057
2025-07-09 15:04:44.711 [E] LiteHttp.c:497 ID 590364354 E_LOGIC : NO need keepAlive
2025-07-09 15:04:44.719 [E] RoomImplX.c:167 operation returned status code: 0x52000057
2025-07-09 15:04:44.811 [E] RoomImplX.c:167 operation returned status code: 0x52000057
I (4744) volc_rtc: join channel success liuxing elapsed 162 ms now 162 ms
I (4745) volc_rtc: join room success
I (4745) MODEL_LOADER: The storage free size is 16384 KB
I (4749) MODEL_LOADER: The partition size is 4152 KB
I (4753) MODEL_LOADER: Successfully load srmodels
I (4758) AFE_CONFIG: Set WakeNet Model: wn9s_nihaoxiaozhi
I (4763) AFE_CONFIG: Set Second WakeNet Model: wn9s_nihaoxiaozhi
I (4769) RAW_OPUS_ENC: Raw Opus encoder init
I (4773) RECORDER_SR: The first wakenet model: wn9s_nihaoxiaozhi
I (4774) volc_rtc: remote user mute audio liuxing:liuxing123 0
I (4779) RECORDER_SR: The second wakenet model: wn9_hilexin
I (4785) volc_rtc: remote user mute video liuxing:liuxing123 1
/********** General AFE (Audio Front End) Parameter **********/
pcm_config.total_ch_num: 4
pcm_config.mic_num: 2: [ ch1, ch3 ]
pcm_config.ref_num: 1: [ ch0 ]
pcm_config.sample_rate: 16000
afe_type: SR
afe_mode: LOW COST
afe_perferred_core: 0
afe_perferred_priority: 5
afe_ringbuf_size: 50
memory_alloc_mode: 3
afe_linear_gain: 1.0
debug_init: false
fixed_first_channel: false
/********** AEC (Acoustic Echo Cancellation) **********/
aec_init: true
aec mode: SR_LOW_COST
aec_filter_length: 4
/********** SE (Speech Enhancement, Microphone Array Processing) **********/
se_init: false, model: BSS
/********** NS (Noise Suppression) **********/
ns_init: false
ns model name: WEBRTC
/********** VAD (Voice Activity Detection) **********/
vad_init: false
vad_mode: 3
vad_model_name: NULL
vad_min_speech_ms: 128
vad_min_noise_ms: 1000
vad_delay_ms: 128
vad_mute_playback: false
vad_enable_channel_trigger: false
/********** WakeNet (Wake Word Engine) **********/
wakenet_init: false
wakenet_model_name: wn9s_nihaoxiaozhi
wakenet_model_name_2: wn9_hilexin
wakenet_mode: 0
/********** AGC (Automatic Gain Control) **********/
agc_init: false
agc_mode: WEBRTC
agc_compression_gain_db: 9
agc_target_level_dbfs: 9
/**************************************************/
I (4955) AFE: AFE Version: (2MIC_V250113)
I (4955) AFE: Input PCM Config: total 4 channels(2 microphone, 1 playback), sample rate:16000
I (4956) AFE: AFE Pipeline: [input] -> |AEC(SR_LOW_COST)| -> [output]
I (5163) AUDIO_RECORDER: RECORDER_CMD_TRIGGER_START
I (5368) main_task: Returned from app_main()
2025-07-09 15:04:46.834 [E] rx_net_lite_cc_bandwidth_estimation.c:190 lite-cc bandwidth up bandwidth = 4630000
2025-07-09 15:04:48.854 [E] rx_net_lite_cc_bandwidth_estimation.c:190 lite-cc bandwidth up bandwidth = 5000000