Oído: Open-Vocabulary Speech Recognition on a $5 Microcontroller

Researchers submitted Oído, an inference engine that runs open-vocabulary English speech recognition entirely on a $5 ESP32-S3 microcontroller with no neural accelerator, executing a 13M-parameter Conformer-CTC model with int8 weights, per-frame dynamic int8 activations and int8 attention. On LibriSpeech test-clean/test-other the on-device arithmetic reaches 3.70%/8.23% word error rate, within 0.12 points of full precision, and 3.33%/7.15% with an on-chip 1.3M-parameter language model, while a transducer head gives 2.99%/6.67% and an int4 variant fits in 8.3 MB. Measured on a physical board the firmware runs at 1.97x the duration of the audio on one core — accurate but not yet real time, with a 4 s command transcribed about 8.7 s after it ends — and the two-core schedule gives wrong results on silicon and is disabled; code and models are released.

Computer Science Sound Submitted on 9 Oct 2026 Title:Oído: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator View PDF https://arxiv.org/pdf/2610.13447 HTML experimental https://arxiv.org/html/2610.13447v1 Abstract:Speech recognition on low-cost microcontrollers is, in practice, limited to keyword spotting or a fixed list of commands. We present Oído, an inference engine that runs open-vocabulary English speech recognition entirely on an ESP32-S3 240 MHz dual-core Xtensa LX7, 512 KB of SRAM, 8 MB of PSRAM, 16 MB of flash, no neural accelerator . Oído executes a 13M-parameter Conformer-CTC model with int8 weights, per-frame dynamic int8 activations and int8 attention on the chip's SIMD instructions, with a schedule designed around flash and PSRAM bandwidth. On LibriSpeech test-clean/test-other the on-device arithmetic reaches 3.70%/8.23% word error rate WER , within 0.12 points of full precision, and 3.33%/7.15% with an on-chip 1.3M-parameter language model; a transducer head gives 2.99%/6.67% and an int4 variant fits in 8.3 MB. This is 2.3-2.8x fewer errors than the vendor's recognizer on the same chip, and fewer than Whisper this http URL http://tiny.en and Moonshine tiny in full precision on a laptop, including in real noise and reverberation. Measured on a physical board, the firmware runs at 1.97x the duration of the audio on one core, with transcripts identical to an instruction-exact emulator: accurate, but not yet real time a 4 s command is transcribed about 8.7 s after it ends . The two-core schedule gives wrong results on silicon and is disabled. A streaming variant shows partial text while the speaker talks and delivers the final text 4.1-11.1 s after clips of 3.6-10.6 s 7.2-22.4 s in utterance mode at 4.86%/11.03% WER; a Spanish model makes 34-60% fewer errors than multilingual Whisper tiny. Code and models are released. Additional Features Current browse context: cs.SD References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .