# Send Audio to gemma4:e2b **URL:** \ **Category:** AI\ **Tags:** rtl8735b\ **Created:** [September 20, 2026, 5:13am UTC](https://forum.amebaiot.com/t/send-audio-to-gemma4-e2b/5075 "2026-09-20T05:13:29Z")\ **Posts on this page:** 9\ **Page:** 1
**Author:** ![rkuo2000](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/rkuo2000/32/1105_2.png) [@rkuo2000](https://forum.amebaiot.com/u/rkuo2000)\ **Post date:** [September 20, 2026, 5:13am UTC](https://forum.amebaiot.com/t/send-audio-to-gemma4-e2b/5075/1 "2026-09-20T05:13:29Z")
**Application** : AI plush toy **LLM Server** : EdgeAI-Gallery App with gemma4-e2b (on Android phone) **EVB** : AMB82-mini **APK** : [EdgeAI-Gallery .apk](https://drive.google.com/file/d/1ZZL5rcPbMorXRguZVM5wo5bcxpb2_1Ef/view?usp=drive_link) , [EdgeAI-Gallery-1.0.19.zip](https://drive.google.com/file/d/1e22rzmnos_rmvkkbSKjBkJrT7TuyZ9xQ/view?usp=drive_link) added text/image/audio API by codex. **Code:** [Ollama\_sendAudio.ino](https://github.com/rkuo2000/EdgeAI-AmebaPro2/blob/main/Arduino/AMB82-mini/Ollama_sendAudio/Ollama_sendAudio.ino) **Error :** == Rtl8735b IoT Platform == [test mode PG] Download Image over UART1[tx=4,rx=3] baud=115200 == Rtl8735b IoT Platform == [Normal mode] BootFromNORFlash [Start Boot ROM…] === Load PARTBL === === Load Done === === Load ISP\_IQ === [fcs chk pass] ISP\_IQ @ 0x8461080, 0x2ff80, 0x0 mfcs\_data version 0x00010001 fcs\_data version 0x00010101 === Process ISP\_IQ === === Load Done === === Load BL === [Image Start Table @ 0x18200] === Load Done === == Boot Loader == Sep 14 2026:19:14:06 === Load FCS Para === === Load Done === [crc pass] === Load ISP\_IQ Sensor === ISP\_IQ @ 0x8461080, 0x2ff80 === Process ISP\_IQ === === Load Done === === Load FW1 === FW\_ISP\_IQ @ 0x8061080, 0x31f80 === Process FW\_ISP\_IQ === DRAM\_TYPE is DDR2 128MB. ddr\_freq = 533 VOE flash @ 0x8093080, 0x82f80 FCS KM\_status 0x00002081 err 0x0000200a Wait KM fcs done 0 us FCS TM\_status 0x003f0000 store fcs data for application It don’t do the sensor initial process RAM TM\_STATUS 0x00bf1208 err 0x00001208 read fcs\_status 0x000000bf read fcs\_status 0x000000bf === Process VOE IMG === [Image Start Table @ 0x20106200] RAM Load @ 0x8116100-\>0x20106200, 0x5dac DDR Load @ 0x811c080-\>0x70100000, 0x252e0a === FW Load Done === Boot Loader \<== == RAM Start == Build @ 19:07:52, Sep 14 2026 set ASP print off $8735b\>set ASP print off Attempting to connect to SSID: HITRON-DF90-2.4G interface 0 is initialized interface 1 is initialized cfg\_size\_lib = 124, cfg\_size\_user = 124 Initializing WIFI …[Driver]: [HALMAC] 11692M HALMAC\_MAJOR\_VER = 1 HALMAC\_PROTOTYPE\_VER = 4 HALMAC\_MINOR\_VER = 20 HALMAC\_PATCH\_VER = [Driver]: The driver include MP [Driver]: Ver = libwlan:2026.09.14.19.30\_b9.6\_b5e42ffdfe93d306926f1a3b54269d29d305b1bf RFE type = 0 start\_addr=(0x4000), end\_addr=(0x8000), buffer\_size=(0x4000), smp\_number\_max=(2048) WIFI initialized [Driver]: set ssid [HITRON-DF90-2.4G] [Driver]: rtw\_joinbss\_cmd MGMT\_FRAME\_PROTECTION\_OPTIONAL no pmf. [Driver]: Bcn (ie: 348, rsn: 0, wpa: 0) ch: 11, seq: 1432, ts: 1890011955211 [Driver]: start auth to f8:34:5a:ab:df:98 [Driver]: auth success, start assoc [Driver]: listen\_interval: 10, bcn\_interval: 100 [Driver]: association success(res=4) [Driver]: set pairwise key to hw: alg:4(WEP40-1 WEP104-5 TKIP-2 AES-4) [Driver]: set group key to hw: alg:4(WEP40-1 WEP104-5 TKIP-2 AES-4) keyid:2 (0) Scan: 1, Auth: 1, Assoc: 1, 4way: 1, connect: 1, reason: 0 [Driver]: TSFValue = 1890016153612, tsf = 0, shift\_set= 0x8000, bcn int = 100 Interface 0 IP address : 192.168.0.19 [LwIP\_DHCP] dhcp offered\_t0\_lease: 604800[video\_voe\_presetting] fps:30 w:1920 h:1080 fwin(1),enc\_en(0),IQ\_OFFSET = 0x17b60 fwin(1),enc\_en(0),SENSOR\_OFFSET = 0x2fba0 sensor id 1 iq\_data 17b60 sensor\_data 2fba0 Register disk driver to Fatfs. FATFS Register: disk driver 0 SD\_Init 0 part\_count = 0 Audio begin [State] Listening… Mic Level: 266 Mic Level: 348 Mic Level: 11082 > > > TRIGGERED \<\<\< > > > [State] Listening Stopped. > > > [State] Recording Setup > > > ctx-\>enc\_info.frameLength \* 2 = 2048 hal\_voe\_ready 0x0 0xbf1208 read fcs\_status 0x000000bf [video\_init] uvcd iq is null, use default. [video\_init] uvcd SNR is null, use default. IQ:FW size (98342) sensor:date 2026/6/29 version:RTL8735B\_VOE\_1.7.1.0 sensor:FW size (5472) sensor timestamp: 2026/06/29 iq timestamp: 2023/05/15 14:48:54 voe\_heap malloc 0x707d9f00, size 21994496 ISP:1 ENC:1 H265:1 NN:1 hal\_voe\_ready 0x0 0xbf1208 voe :RTL8735B\_VOE\_1.7.1.0 sensor:RTL8735B\_VOE\_1.7.1.0 hal :RTL8735B\_VOE\_1.7.1.0 load time sensor:69us iq:1217us itcm:0us dtcm:0us ddr:0us ddr2:0us Set H264 default HIGH profile rc\_version RC\_v1 [video\_pre\_init\_procedure] START hal\_voe\_send2voe too long 38866 cmd 0x00000206 p1 0x00000000 p2 0x00000000 VOE command 0x206 fail ret 0x0 Start MP4 recording (1 files) STORAGE\_INIT open file (0:/TestRecordingAudioOnly.mp4) len = 5 seconds STORAGE\_INIT → STORAGE\_START Stop MP4 recording finish output task hal\_video\_output\_task closed VOE command 0x207 fail ret 0x0 hal\_voe\_ready 0x0 0x1718 aac reset ctx-\>enc\_info.frameLength \* 2 = 2048 **[Error] Recording did not start or timed out.** [State] Listening… Mic Level: 409 Mic Level: 339 Mic Level: 394 Mic Level: 417 Mic Level: 320 Mic Level: 341 Mic Level: 423 Mic Level: 419 Mic Level: 533 ---
**Author:** ![system](https://us1.discourse-cdn.com/flex016/uploads/ameba/original/2X/7/7009caf971627f868f3de3d34312aff2d14c61e3.png) [@system](https://forum.amebaiot.com/u/system)\ **Post date:** [September 20, 2026, 5:13am UTC](https://forum.amebaiot.com/t/send-audio-to-gemma4-e2b/5075/2 "2026-09-20T05:13:32Z")
👋 Thanks for posting! For documentation, SDK resources, FAQs, and community guidelines, please visit: [here](https://forum.amebaiot.com/t/forum-community-guidelines-and-resources/4969) For commercial users, if you would like to have dedicated technical support or to connect with us, please fill in the [Private User Form](https://forms.cloud.microsoft/r/FK9WxDhvDg) Happy building with Ameba! * * * 👋 感謝您的分享！ 如需查閱技術文件、SDK 資源、常見問題及社群指南，請參考: [這裡](https://forum.amebaiot.com/t/forum-community-guidelines-and-resources/4969) 若您是商業用戶，希望獲得專屬技術支援或與我們聯繫，請填寫 [Private User Form (商業用戶表單)](https://forms.cloud.microsoft/r/FK9WxDhvDg) 祝您使用 Ameba 開發順利！ ---
**Author:** ![KevinKL](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/kevinkl/32/2632_2.png) [@KevinKL](https://forum.amebaiot.com/u/KevinKL)\ **Post date:** [September 24, 2026, 10:15am UTC](https://forum.amebaiot.com/t/send-audio-to-gemma4-e2b/5075/3 "2026-09-24T10:15:58Z")
Hi @rkuo2000 , Thanks for sharing the code and APK. Upon checking, the MP4 recording failure is due to incorrect configuration for mp4 object. For audio-only recording, calling of `mp4.setRecordingDataType(STORAGE_AUDIO);` is necessary. Please find the attached modified code for reference, the recording error should be resolved if the configurations are correct. [Ollama\_sendAudioOnly.zip](https://forum.amebaiot.com/uploads/short-url/vE2CTSa1WefReItuwaTKWMEYQ7I.zip) (3.9 KB) Thank you. ---
**Author:** ![rkuo2000](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/rkuo2000/32/1105_2.png) [@rkuo2000](https://forum.amebaiot.com/u/rkuo2000)\ **Post date:** [September 24, 2026, 2:37pm UTC](https://forum.amebaiot.com/t/send-audio-to-gemma4-e2b/5075/4 "2026-09-24T14:37:56Z")
Problem 1. HUB8735-Ultra did not support micLevel /home/rkuo/Arduino/AMB82-mini/Ollama\_sendAudioOnly/Ollama\_sendAudioOnly.ino: In function ‘void doListening()’: /home/rkuo/Arduino/AMB82-mini/Ollama\_sendAudioOnly/Ollama\_sendAudioOnly.ino:134:32: error: ‘class Audio’ has no member named ‘micLevel’ 134 | int currentVol = audio.micLevel(); | ^ ~~~~~~~ exit status 1 Compilation error: ‘class Audio’ has no member named ‘micLevel’ Problem 2. AMB82-mini receive Error from gemma4 [Error] Ollama HTTP status: 400 {“error”:{“message”:“Malformed JSON or media data”}} (the working python code is [ollama\_audio.py](https://github.com/rkuo2000/AI-exercise/blob/main/code/ollama_audio.py) for your reference) See below console messages: == Rtl8735b IoT Platform == [test mode PG] Download Image over UART1[tx=4,rx=3] baud=115200 == Rtl8735b IoT Platform == [Normal mode] BootFromNORFlash [Start Boot ROM…] === Load PARTBL === === Load Done === === Load ISP\_IQ === [fcs chk pass] ISP\_IQ @ 0x8461080, 0x2ff80, 0x0 mfcs\_data version 0x00010001 fcs\_data version 0x00010101 === Process ISP\_IQ === === Load Done === === Load BL === [Image Start Table @ 0x18200] === Load Done === == Boot Loader == Sep 14 2026:19:14:06 === Load FCS Para === === Load Done === [crc pass] === Load ISP\_IQ Sensor === ISP\_IQ @ 0x8461080, 0x2ff80 === Process ISP\_IQ === === Load Done === === Load FW1 === FW\_ISP\_IQ @ 0x8061080, 0x31f80 === Process FW\_ISP\_IQ === DRAM\_TYPE is DDR2 128MB. ddr\_freq = 533 VOE flash @ 0x8093080, 0x82f80 FCS KM\_status 0x00002081 err 0x0000200a Wait KM fcs done 0 us FCS TM\_status 0x003f0000 store fcs data for application It don’t do the sensor initial process RAM TM\_STATUS 0x00bf1208 err 0x00001208 read fcs\_status 0x000000bf read fcs\_status 0x000000bf === Process VOE IMG === [Image Start Table @ 0x20106200] RAM Load @ 0x8116100-\>0x20106200, 0x5a6c DDR Load @ 0x811c080-\>0x70100000, 0x234a2a === FW Load Done === Boot Loader \<== == RAM Start == Build @ 14:56:20, Sep 22 2026 set ASP print off $8735b\>set ASP print off Attempting to connect to SSID: HITRON-DF90-2.4G interface 0 is initialized interface 1 is initialized cfg\_size\_lib = 124, cfg\_size\_user = 124 Initializing WIFI …[Driver]: [HALMAC] 11692M HALMAC\_MAJOR\_VER = 1 HALMAC\_PROTOTYPE\_VER = 4 HALMAC\_MINOR\_VER = 20 HALMAC\_PATCH\_VER = [Driver]: The driver include MP [Driver]: Ver = libwlan:2026.09.22.14.53\_bmaster\_78146548989f20fdbd7286451d67429c855d2a94 RFE type = 0 start\_addr=(0x4000), end\_addr=(0x8000), buffer\_size=(0x4000), smp\_number\_max=(2048) WIFI initialized [Driver]: set ssid [HITRON-DF90-2.4G] [Driver]: rtw\_joinbss\_cmd MGMT\_FRAME\_PROTECTION\_OPTIONAL no pmf. [Driver]: Bcn (ie: 348, rsn: 0, wpa: 0) ch: 11, seq: 1462, ts: 2268444057617 [Driver]: start auth to f8:34:5a:ab:df:98 [Driver]: auth success, start assoc [Driver]: listen\_interval: 10, bcn\_interval: 100 [Driver]: association success(res=2) [Driver]: set pairwise key to hw: alg:4(WEP40-1 WEP104-5 TKIP-2 AES-4) [Driver]: set group key to hw: alg:4(WEP40-1 WEP104-5 TKIP-2 AES-4) keyid:1 (0) Scan: 1, Auth: 1, Assoc: 1, 4way: 1, connect: 1, reason: 0 Interface 0 IP address : 192.168.0.19 [LwIP\_DHCP] dhcp offered\_t0\_lease: 604800[Driver]: TSFValue = 2268445081617, tsf = 0, shift\_set= 0x8000, bcn int = 100 Register disk driver to Fatfs. FATFS Register: disk driver 0 SD\_Init 0 part\_count = 0 Audio begin [State] Listening… Mic Level: 315 Mic Level: 428 Mic Level: 473 Mic Level: 14426 Mic Level: 14426 > > > TRIGGERED \<\<\< > > > [State] Listening Stopped. > > > [State] Recording Setup > > > ctx-\>enc\_info.frameLength \* 2 = 2048 Start MP4 recording (1 files) STORAGE\_INIT open file (0:/TestRecordingAudioOnly.mp4) len = 5 seconds STORAGE\_INIT → STORAGE\_START STORAGE\_START 4 INFO: No udta box callback defined. Skipping udta box. STORAGE\_STOP video\_len = 0 audio\_len = 40 moov\_len = 1661 total\_size = 20201 STORAGE\_STOP → STORAGE\_IDLE aac reset ctx-\>enc\_info.frameLength \* 2 = 2048 [State] Recording Done [State] Sending audio to Ollama… SD\_DeInit Connect to 192.168.0.13 [INFO] Connect to Server successfully! [INFO] Audio sent; waiting for transcription… [Error] Ollama HTTP status: 400 {“error”:{“message”:“Malformed JSON or media data”}} [State] Returning to Listen Mode [State] Listening… Mic Level: 325 Mic Level: 429 ---
**Author:** ![KevinKL](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/kevinkl/32/2632_2.png) [@KevinKL](https://forum.amebaiot.com/u/KevinKL)\ **Post date:** [September 25, 2026, 4:02am UTC](https://forum.amebaiot.com/t/send-audio-to-gemma4-e2b/5075/5 "2026-09-25T04:02:08Z")
Hi @rkuo2000 , **Problem 1: HUB8735-Ultra did not support micLevel** As the Arduino SDK for HUB8735 is outdated, you may try to apply this [patch](https://drive.google.com/file/d/10sATLeEDRQY0OX3-i0nyfKsw-6qj0zX6/view?usp=sharing) for the updated API. If you still encounter error when running example, you might need to request for version sync between the HUB8735 SDK and ameba-arduino-pro2. **Problem 2. AMB82-mini receive Error from gemma4** **Issue : 400 Malformed JSON or media data** The request body was built by **serializing a full ArduinoJson document, then hand-trimming the last 4 bytes** with fixed byte arithmetic: ```cpp prefix.remove(prefix.length() - 4); // which 4 chars? WRONG prefix += ",{\"type\":\"input_audio\",\"input_audio\":{\"data\":\""; ``` `serializeJson` ends with **6** terminal chars (`"}]}]}`), so `remove(4)` chopped **inside the `"text"` string’s closing quote** , splicing the audio object into the value: ```json "text":"Transcribe the audio,{"type":"input_audio","input_audio":{"data":"... ``` → invalid JSON → the Gallery server correctly rejected it with `400`. Solution Build the whole body as **one ArduinoJson document** — no string arithmetic: ```cpp doc["model"] = model; doc["stream"] = false; JsonArray messages = doc["messages"].to(); JsonObject userMsg = messages.add(); userMsg["role"] = "user"; JsonArray content = userMsg["content"].to(); JsonObject textPart = content.add(); textPart["type"] = "text"; textPart["text"] = prompt; JsonObject audioPart = content.add(); audioPart["type"] = "input_audio"; JsonObject audioData = audioPart["input_audio"].to(); audioData["data"] = encodedData; // base64 audioData["format"] = "mp4"; serializeJson(doc, requestBody); // valid JSON, real length() // HTTP Content-Length = requestBody.length(), sent via writeAll() ``` Verified valid request: ```json {"model":"gemma4:e4b","stream":false,"messages":[{"role":"user","content":[ {"type":"text","text":"Transcribe the audio"}, {"type":"input_audio","input_audio":{"data":"","format":"mp4"}}]}]} ``` **Issue — 2nd recording fails** SD card was being unmounted between cycles - The upload code called `fs.end()` after reading, and in `AmebaFatFS.cpp`: ```cpp void AmebaFatFS::end(void) { fatfs_sd_close(); memset(&fatfs_sd, 0, sizeof(fatfs_sd_params_t)); fatfs_sd.drv_num = -1; sd_gpio_deinit(); // ← de-inits the SD host GPIO } ``` - After the first upload, the SD host was powered down. The next `mp4.begin()` → `f_open("0:/Clip2.mp4")` failed because the disk driver was no longer registered, and the muxer logged `Can't open the file`. Solution **Never unmount the SD card** in the sketch. Remove every `fs.end()` call on the upload path, so the disk stays mounted for the whole sketch lifetime: - `fs.begin()` runs once (first send / whenever it’s missing). - Every error path just `return` — the next trigger’s `mp4.begin()` always finds the disk registered. - Uploaded clips are deleted after a successful transcription, but the disk stays mounted. Please find the following attached fixed sample code for reference. Thank you. [Ollama\_sendAudio\_Fixed.zip](https://forum.amebaiot.com/uploads/short-url/lcbtQvQ5Cf55Fh09MwIgosmvUVw.zip) (5.5 KB) ---
**Author:** ![rkuo2000](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/rkuo2000/32/1105_2.png) [@rkuo2000](https://forum.amebaiot.com/u/rkuo2000)\ **Post date:** [September 25, 2026, 6:20am UTC](https://forum.amebaiot.com/t/send-audio-to-gemma4-e2b/5075/6 "2026-09-25T06:20:51Z")
@KevinKL , Ollama\_sendAudio\_Fixed.zip works for AMB82-mini but HUB8735-Ultra failed, audioLevel not triggering. Due to AMB82-Mini dimension did not fit in OpenDuck-Mini form factor, (also some small robot projects will need to use HUB8735-Ultra to fit in) I still need HUB8735-Ultra working with gemma4:e2b. ---
**Author:** ![KevinKL](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/kevinkl/32/2632_2.png) [@KevinKL](https://forum.amebaiot.com/u/KevinKL)\ **Post date:** [September 25, 2026, 6:50am UTC](https://forum.amebaiot.com/t/send-audio-to-gemma4-e2b/5075/7 "2026-09-25T06:50:39Z")
Hi @rkuo2000 , Thanks for verifying. Would you mind providing the logs for HUB8735B-Ultra? ---
**Author:** ![rkuo2000](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/rkuo2000/32/1105_2.png) [@rkuo2000](https://forum.amebaiot.com/u/rkuo2000)\ **Post date:** [September 25, 2026, 8:12am UTC](https://forum.amebaiot.com/t/send-audio-to-gemma4-e2b/5075/8 "2026-09-25T08:12:46Z")
the patch AudioStream.h AudioStream.cpp can not directly replace HUB8735-Ultra’s code, because their audio are different. OTA also incompatible /home/rkuo/.arduino15/packages/ideasHatch/hardware/AmebaPro2/4.1.1-Release/libraries/OTA/src/ota\_drv.c: In function ‘http\_update\_ota\_task’: /home/rkuo/.arduino15/packages/ideasHatch/hardware/AmebaPro2/4.1.1-Release/libraries/OTA/src/ota\_drv.c:34:15: warning: implicit declaration of function ‘https\_update\_ota’; did you mean ‘http\_update\_ota’? [-Wimplicit-function-declaration] 34 | ret = https\_update\_ota((char \*)\_server, \_port, (char \*)resource); | ^ ~~~~~~~~~~~~~~~ | http\_update\_ota Interface 0 IP address : 192.168.0.15 Register disk driver to Fatfs. FATFS Register: disk driver 0 SD\_Init 0 part\_count = 0 Audio begin (STORAGE\_AUDIO, trigger recording) [State] Listening… Mic Level: 36 Mic Level: 38 Mic Level: 40 Mic Level: 33 Mic Level: 39 Mic Level: 40 ---
**Author:** ![KevinKL](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/kevinkl/32/2632_2.png) [@KevinKL](https://forum.amebaiot.com/u/KevinKL)\ **Post date:** [September 30, 2026, 9:05am UTC](https://forum.amebaiot.com/t/send-audio-to-gemma4-e2b/5075/9 "2026-09-30T09:05:52Z")
Hi @rkuo2000 , Would you mind replacing the pre-compiled libraries with the latest version from [ameba-arduino-pro2/Arduino\_package/hardware/variants/common\_libs at dev · Ameba-AIoT/ameba-arduino-pro2 · GitHub](https://github.com/Ameba-AIoT/ameba-arduino-pro2/tree/dev/Arduino_package/hardware/variants/common_libs) ? > [@rkuo2000](#): > > the patch AudioStream.h AudioStream.cpp can not directly replace HUB8735-Ultra’s code, > because their audio are different. Kindly patch according to the required changes, ensure that the pins and board specific configurations remain unchanged. Thank you.