17MB model beats human experts at pronunciation scoring
This app lets you record or upload an audio clip and type the expected text to receive a detailed pronunciation score, word‑by‑word feedback, and phoneme analysis. It can also turn spoken audio int...
17MB model beats human experts at pronunciation scoring launched on February 20, 2026 with 13 votes, #893 of 16,627 launches that month and more than 90% of that year's launches.
In plain words
This is a pronunciation scoring model available on Hugging Face that weighs only 17MB. It automatically evaluates speech pronunciation and performs at a level comparable to human experts. The model is designed for language learners and educational applications that need fast, automated assessment of spoken English accuracy without requiring large computational resources.
written from the facts on this page · September 2026
From the sources
Speech AI is a complete speech processing platform with three APIs: • Pronunciation Assessment — phoneme-level scoring, 17MB model, beats human experts • Speech-to-Text — word timestamps + confidence scores, same 17MB model • Text-to-Speech — 12 English voices via Kokoro-82M (#1 TTS Arena, Apache 2.0) All three ship as an MCP server with 8 tools, so AI agents can assess, transcribe, and speak in one integration. REST API and Azure Marketplace also available.
Does a similar job
all alternatives →- ITI trained a 9M speech model to fix my Mandarin tonesJan 2026 · simedw.com · ▲469
Built this because tones are killing my spoken Mandarin and I can't reliably hear my own mistakes. It's a 9M Conformer-CTC model trained on ~300h (AISHELL + Primewords), quantized to INT8 (11 MB), runs 100% in-browser via ONNX Runtime Web. Grades per-syllable pronunciation + tones with Viterbi forced alignment. Try it here: https://simedw.com/projects/ear/
Conversational AI 2.0 From ElevenLabs2025 · elevenlabs.io · ▲652Luke from ElevenLabs here. We just released Scribe Realtime v2, our new real-time Speech to Text model. We rebuilt it from the ground up around a new architecture that uses predictive transcription – it anticipates the next likely word before it’s spoken. That makes it both fast (around 150 ms latency) and highly accurate. Scribe v2 Realtime outperforms every low latency transcription model across 30 commonly used EU and Asian languages – 93.5% accuracy, compared to Gemini 2.5 Flash (91.4%), GPT-4o MiniTranscribe (90.7%), and Deepgram Nova 3 (85%). It supports 90+ languages including…
Kitten TTS – 25MB CPU-Only, Open-Source TTS Model2025 · github.com · ▲1,003Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Speech Meter – Improve Your English Pronunciation2023 · speechmeter.com · ▲71Hey HN! We built Speech Meter as a tool to practice and improve English pronunciation. It uses AI to analyze your accent and score your pronunciation accuracy. It’s great for anyone who wants to practice their pronunciation in English. I’d love to hear your thoughts and suggestions for improvements. I really appreciate any feedback you could have (:
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗
Launched alongside, February 2026
the whole month →
Lovon AI Therapy▲801Feel closer and have more fun with your partner every day!
AI · Feb 2026 · lovon.app
Hello my name is Ben Ward for the past 3 years I have been remastering the financial game Wall Street Raider created by Michael Jenkins originally on DOS in 1986. It has been a rough journey but I finally see the light at the end of the tunnel. I just recently redid the website and thought maybe the full story of how this project came to be would interest you all. Thank you for reading.
Work · Feb 2026 · wallstreetraider.com