Shruti Konkani
Speech to text for Konkani and English, on your device, with no server.
Try it now · in your browser · free, no login
Speak Konkani, English or both. Shruti Konkani writes it down on your device.
Shruti · checking this device
Audio never leaves your device. Shruti and its open-source engine run inside this page.
(or drop one on the transcript)
Load Shruti, then press Record and speak Konkani, English or both.
Speak Konkani, English or both. English words can stay in English (Latin script) and are underlined here; Konkani is written in Devanagari, not Romi or Kannada script. While you speak, words appear once they have settled, a second or two behind you; when you stop, Shruti reads the whole recording once more for the final text.
Shruti Konkani · 29.7 MB · Konkani and English · 7 November 2026
Konkani and English in one 29.7 MB file. On Konkani conversations, about 15% fewer errors than IndicConformer Konkani, a model almost five times its size.
Shruti Konkani writes Konkani in Devanagari, and about half of the English words stay in English letters: बांगडे आनी सुंगटां fridge भितर दवरल्यात. On real conversations (DiarBench, held out, 90 turns), counting English words only in English letters, its word error rate is 40.0, against IndicConformer Konkani’s 47.0, the one rival we measured. It writes about half of the English words in English letters (49.6%); IndicConformer Konkani writes none. It runs offline on a five-year-old phone, about 12× faster than real time in 64 MB of memory with the native engine, and it invented no words on 100 silent clips.
| Model | File | IndicVoices valid | DiarBench, English in English | DiarBench, native |
|---|---|---|---|---|
| Shruti Konkani | 29.7 MB | 41.4 | 40.0 | 47.3 |
| IndicConformer Konkani | 137.7 MB | 33.4 | 47.0 | 37.3 |
Word error rate %, lower is better; DiarBench 90 turns, the same scorer for every model, measured 3 November 2026. IndicVoices valid is IndicVoices’ own held-out split: its speakers are kept out of training and its sentences blocked, but it is the same source as our training data, so it flatters us. DiarBench is real conversation from outside it: 90 turns from 23 conversations, 1,457 reference words, 278 of them English, in 71 turns. The English-in-English column scores against references that write English words in English (Latin script), and English words count only if written in English letters; the native column scores against references that write those English words in Devanagari. Other Konkani speech models exist that we have not measured; these results cover only the models listed here.
Where it falls short
- Devanagari only. Goan Konkani is widely written in Romi too, and this model does not write it. Reubencf/konkani-whisper-stt targets Romi; we have not measured it.
- The native reference shows the gap. IndicConformer Konkani is ahead on DiarBench native (37.3 vs 47.3; +6.41 to +13.71) and on IndicVoices valid (33.4 vs 41.4). Character errors: DiarBench 25.38% vs 11.58%, IndicVoices valid 22.77% vs 10.1%.
- One rival measured. No independent read test was available either: IndicVoices valid shares a source with our training data.
- English words in Devanagari: about 77 of DiarBench’s 278 by automatic alignment (so as सो). DiarBench also glosses some local names in Latin, so a correct native spelling can score as an error.
- In a browser it was tested on 4 lines played into this page on one phone’s Chrome, with the language set. All 4 came out in Devanagari, and 2 kept some English letters. Not yet tested with a live microphone. On the other Shruti languages where we measured it, plain English loses a little accuracy this way.
- No Konkani reader has reviewed this output yet.
- Loud noise: Shruti models sometimes repeat a phrase over and over in loud noise (measured on Shruti Hindi-family models, not on Konkani).
- Not tested on Konkani: noise, music, far-away or speaker-played audio, Linux, Windows and iOS. No punctuation; numbers come out as words.
Try Shruti Konkani Shruti Konkani on Hugging Face the model file, the full results and how each model was run
Use it in your app
Every Shruti model runs in Cactus’s open-source needle engine. Download the engine for your platform and the file for your language, and pass it a WAV file or 16 kHz audio.
# Command line (Mac, Linux, Windows)
# Engine: huggingface.co/Cactus-Compute/needle3, your platform
# Model: shruti-konkani.cact, from Shruti Konkani's Hugging Face repo
./needle --model shruti-konkani.cact --audio clip.wav
# for speech that is only English: --audio-language en
# Python
pip install cactus-needle
import needle
shruti = needle.Whistle(weights="shruti-konkani.cact")
print(shruti.transcribe("clip.wav")["text"])- Android, iOS and the web: call the engine’s C API.
needle_loadtakes the model file,needle_transcribea clip, andneedle_stream_transcribe_processabout a second of live audio at a time. The demo on this page makes the same calls, from WebAssembly in a Web Worker. - Leave the language unset for Hindi and Hinglish: detection does as well as setting it on Hindi, Hinglish, accented Hindi and US English. Set English when the speech is only English with an Indian accent, which detection often takes for Hindi. On a subset of Svarah: 21.13% word errors with English set, 25.75% detected.
- Keywords, one per line, favour the names, places and product words your users say.
- Cactus’s Python package (cactus-needle) sends anonymous usage counts by default; set
NEEDLE_TELEMETRY=0to turn that off. The command-line engine and the WebAssembly engine on this page make no network requests of their own.
Credits
Every Shruti model is built on Cactus Whistle and runs in the needle engine, both by Cactus Compute under Apache-2.0. The engine files on this page are Cactus’s WebAssembly build, unmodified, served with its licence and notice. Shruti Konkani’s model card on Hugging Face lists its training datasets and their licences.