iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Oído is an open-source speech-recognition project designed to transcribe English locally on an ESP32-S3 microcontroller, without a cloud service or a fixed command list. Its maintainers report promising LibriSpeech accuracy, but the speed figures available in the project’s September 30, 2026 status note were still estimates—not measurements from a physical board. To reproduce the documented build, use an ESP32-S3-DevKitC-1 N16R8 and an INMP441 I2S microphone.
What Oído does
Oído is an open-vocabulary, English speech-to-text engine intended to run on an ESP32-S3. “Open vocabulary” means it is not limited to a predefined list of spoken commands. The project describes local processing without cloud transcription or a neural accelerator.
The documented target is a 240 MHz dual-core Xtensa LX7 with 8 MB PSRAM and 16 MB flash. Those are the project’s target specifications, not independent measurements of performance. Its C implementation is tailored to the chip’s vector unit and uses quantized kernels, dual-core scheduling, and utterance segmentation.
Free tools Windows power users keep installed
One-click scans. No signup required.
The model pipeline is described as a log-mel front end, convolutional subsampling, a 16-layer Conformer encoder, and CTC decoding over 1,024 BPE tokens. The engine also supports an RNN-T head and an optional GRU language model used with CTC prefix beam search. The repository and launch post provide the project details: Oído’s GitHub repository and Lokutor’s October 1, 2026 launch post.
#1 Best Overall
- 🔥【Dual Mode & High Performance】 The ESP32-S3 development board features integrated dual-core xtensa 32-bit LX7 microprocessor, clock speed up to 240 MHz, with 16MB Flash and 8 MB PSRAM. Perfect for Arduino IoT projects requiring stable wireless communication with ultra-low power consumption.
- 🔧【Easy Programming & Debugging】 Equipped with dual USB Type-C ports, this ESP32-S3 board supports both USB and UART modes for effortless programming, firmware flashing, and debugging.
- 🌐【Versatile Wireless Connectivity】 Built-in Wi-Fi (2.4GHz) and Bluetooth 5.0 (LE) dual-mode ensure seamless connectivity with a wide range of smart devices, making it ideal for IoT, smart homes projects.
- 🚀【Flexible Download Options】 Supports dual download methods — USB direct download or USB-to-serial download — offering flexibility and convenience for different development needs.Ideal for beginners and developers working with ESP32-S3.
- 🔋【Advanced Power-Saving Modes】 Designed for energy-efficient applications, with 3.3V SPI voltage, the ESP32-S3 board supports multiple low-power modes, allowing you to extend battery life based on different usage scenarios.
What the reported accuracy numbers show
Word error rate (WER) measures transcription errors against a reference transcript; lower is better. The following figures are reported by Lokutor for LibriSpeech’s test-clean and test-other sets using the same text normalization for the listed systems. They are project-reported results, not figures from an independently cited benchmark paper.
| System or configuration | Test-clean WER | Test-other WER | Qualification |
|---|---|---|---|
| Oído NVIDIA Conformer-CTC Small, int8, greedy | 3.7% | 8.2% | On-chip result; project documentation |
| Oído, int4, greedy | 4.6% | 10.0% | On-chip result; project documentation |
| Oído int8 with on-chip language model | 3.3% | 7.2% | On-chip result; project documentation |
| Oído int4 with on-chip language model | 3.8% | 8.4% | On-chip result; project documentation |
| Espressif MultiNet7 | 8.5% | 21.3% | Project table describes a fixed command-list API |
| Moonshine tiny | 5.0% | 12.1% | Laptop baseline; 500 evenly spaced utterances per set |
| Whisper tiny.en | 6.3% | 15.9% | Laptop baseline; 500 evenly spaced utterances per set |
| Vosk small | 9.9% | 21.6% | Laptop baseline; 500 evenly spaced utterances per set |
The repository says its on-chip rows use the full test sets, while the laptop baselines use 500 evenly spaced utterances from each set. That difference makes the laptop comparisons less directly comparable, even though the project applies the same text normalization to the listed results.
Rank #2
- ESP32-S3-DevKitC-1-N16R8 SPI voltage: 3.3v, ESP32-S3-DevKitC-1 is an entry-level development board equipped with Wi-Fi + Bluetooth module ESP32-S3
- Most of the I/O pins on the module are broken out to the pin headers on both sides of this board for easy interfacing. Developers can either connect peripherals with jumper wires or mount ESP32-S3-DevKitC on a breadboard.
- The ESP32-S3-DevKitC development board equipped with ESP32-S3-DevKitC-1-N16R8, a general-purpose Wi-Fi + Bluetooth LE MCU module that integrates complete Wi-Fi and Bluetooth LE functions.
- ESP32-S3-N16R8 cable can be used: USB Type A to Type-C cable or CC cable Note the distinction between the commonly used USB A port to Type-C cable that can only be charged, which cannot be used for communication between YD-ESP32-S3 and the host.
- USB-to-UART Port and ESP32-S3 USB Port (either one or both), default power supply (recommended)
The results are evidence about those test sets and configurations—not a guarantee for arbitrary microphones, accents, room acoustics, or conversations. The README identifies English-only recognition and says very noisy crowds and reverberant rooms are difficult conditions. It also describes utterance-level output rather than word-by-word streaming.
How fast and small is it on the ESP32-S3?
As of the repository status note dated September 30, 2026, physical-board speed measurements were still expected in the following days. The project estimates a real-time factor of 0.7–0.95 from QEMU instruction counts and assumed cycle and stall behavior. This is an emulator-based estimate, not a measured silicon result; a real-time factor below 1 would indicate processing faster than the audio duration under the conditions measured.
Rank #3
- 【Low-power performance】: The AYWHP ESP32-S3 Core development board integrates a 2.4 GHz Wi-Fi and Bluetooth 5 (LE) dual-mode communication module, perfect for Arduino Internet of Things (IoT) projects.
- 【Simple programming and debugging】: The ESP32-S3 module makes it easy to program and burn in your ESP32-S3 board via dual USB Type-C ports, with a choice of USB or UART modes.
- 【Multiple Power Saving Modes】: The ESP S3 development board supports multiple low-power modes, which can be configured according to different application scenarios to provide longer battery life.
- 【Dual download modes】: The ESP S3-1 module supports both USB direct connection download and USB to serial port download, providing more flexibility and convenience.
- 【Diverse connectivity options】: The ESP32-S3-1 supports dual-mode Wi-Fi and Bluetooth 5.0 (LE) connectivity for a wide range of smart devices, making it ideal for Internet of Things (IoT) applications.
Lokutor also reports approximately 2.4 MB of peak working memory for a 20-second utterance, measured in QEMU. Its named model sizes are 14.0 MB for int8 and 8.3 MB for int4. These are project-reported figures; the memory result is specifically an emulator measurement, and the repository’s status note does not establish physical-board speed.
Hardware required for the documented build
The project specifies one particular development-board memory configuration. An arbitrary ESP32-S3 board should not be assumed to have the required memory.
Rank #4
- 【ESP32-S3 PERFORMANCE】Dual-core 240MHz processor with 16MB Flash and 8MB PSRAM for IoT, AI, and machine learning projects.
- 【WIRELESS CONNECTIVITY】Onboard antenna for 2.4GHz WiFi and Bluetooth 5.0 LE — for smart home devices, no external antenna needed.
- 【LEAD-FREE GOLD EDITION DESIGN】Immersion gold (ENIG) plating for durability and conductivity. Lead-free, RoHS-compliant — for long-term prototyping.
- 【PRE-SOLDERED, PLUG-IN DESIGN】ESP32-S3 boards come with pre-soldered headers and plug directly into the included expansion and terminal boards — no soldering required.
- 【MULTI-PLATFORM COMPATIBILITY】Works with C++, MicroPython, ESP-IDF, Raspberry Pi, and STM32 — with online tutorials for quick start. Power via USB-C (5V) or VIN pin (5–12V); do not exceed 5V on the USB-C ports.
- Board: ESP32-S3-DevKitC-1 N16R8, with 16 MB flash and 8 MB PSRAM.
- Microphone: INMP441 I2S microphone, connected as SCK to GPIO4, WS to GPIO5, SD to GPIO6, and L/R to ground.
- Optional display: 0.96-inch SSD1306 OLED, connected over I2C with SDA on GPIO8 and SCL on GPIO9. It can show transcript text.
Check the board’s exact N16R8 memory variant and the microphone’s compatibility with the documented wiring before assembling the setup. The OLED is optional, not a prerequisite for recognition.
Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Scan for outdated or missing drivers - takes under a minute3Repair Windows errors before they cause bigger problemsYou can also explore the engine without buying the board: Lokutor says its laptop host build can run the chip’s arithmetic and supports a live-microphone demo. That can help with experimentation, but it does not establish how fast inference will run on physical ESP32-S3 hardware.
Best Value
- 【GOLD EDITION — IMMERSION GOLD PCB】The Lonely Binary Gold Edition features a black PCB with lead-free immersion gold (ENIG) plating and clear silkscreen — the signature finish of the Lonely Binary Gold Edition line. RoHS-compliant.
- 【16MB FLASH + 8MB PSRAM】Large memory capacity for OTA updates, large programs, and AI/ML tasks — more headroom than 4MB boards for data-intensive IoT and automation projects.
- 【EXTERNAL IPEX ANTENNA】External IPEX antenna can be positioned for extended WiFi and Bluetooth signal coverage — for remote applications like weather stations, robots, or enclosed builds.
- 【DUAL USB TYPE-C PORTS】Separate power and data ports for macOS, Windows, and Linux. Power via USB-C (5V) or VIN pin (5–12V); do not exceed 5V on the USB-C ports.
- 【FLEXIBLE PROTOTYPING PINS】2x40-pin GPIO headers compatible with breadboards and sensors. Supports external ToF sensors via I2C for distance sensing.
Licenses and use in a product
The repository assigns different licenses to the engine and model assets. Review the current notices and the terms for the exact files you plan to distribute; do not assume that licensing the code also covers every model.
| Component | License stated by the repository |
|---|---|
| Engine code | GPLv3 |
| Int8 model | CC-BY-4.0 |
| Int4 model | CC-BY-SA-4.0 |
| Language model | CC-BY-4.0 |
Lokutor says it offers commercial licensing and integration support for products that cannot meet GPLv3 terms. That is the project author’s statement, not independent legal advice. Device makers should assess the applicable code and model terms for their intended distribution and obtain qualified legal guidance when needed.
Who should consider Oído?
Oído is worth evaluating if you need local, open-vocabulary English transcription on a tightly constrained microcontroller and can work with the specified hardware and an utterance-based interface. Its reported accuracy is promising, but the status note available on September 30, 2026 had not yet established physical-board speed. For an application that depends on immediate streaming, broad language coverage, or reliable transcription in noisy or reverberant spaces, the project’s documented limits are central to the decision.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
