Shruti
Speech to text that runs on your device, with no server: one small model per language, each with English.
Speech to text in one small file per language, each with English: Shruti Hindi (Hindi, English and Hinglish, 29.5 MB), Shruti Marathi (Marathi and English, 29.7 MB), Shruti Tamil (Tamil and English, 29.7 MB), Shruti Bengali (Bengali and English, 29.7 MB) and Shruti Telugu (Telugu and English, 29.7 MB). Each writes its own language in its own script and English words in English, the way people type, and runs offline: on a phone, on a laptop or in a browser tab.
Try it now · in your browser · free, no login
Speak Hindi, English or both. Shruti 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 Hindi, English or both.
The language is detected for you. English words stay in English (Latin script) and are underlined here; Hindi is written in Devanagari. 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.
Languages
One model per language, each with English, listed in the order they came out. Each is its own small file, so an app or a browser downloads only the language it needs. Every result below was measured by us, with the same test sets and scorer for every model in its table.
Shruti Hindi
Hindi, English and Hinglish · 29.5 MB · 19 October 2026
100× smaller than OpenAI’s Whisper large-v3, with fewer word errors on the same Hindi test clips.
Larger Hindi-only models are more accurate on pure Hindi, and Whisper large-v3 on English.
Shruti Marathi
Marathi and English · 29.7 MB · 2 November 2026
The most accurate open Marathi speech-to-text model under 100 MB that we measured.
IndicConformer Marathi, about 5× larger, makes fewer errors on pure Marathi.
Shruti Tamil
Tamil and English · 29.7 MB · 3 November 2026
The most accurate open Tamil speech-to-text model under 100 MB that we measured.
IndicConformer Tamil, about 5× larger, makes fewer errors on pure Tamil.
Shruti Bengali
Bengali and English · 29.7 MB · 3 November 2026
On conversations that mix in English, fewer errors than Bengali models three and five times its size.
On read Bengali, Vosk Bengali, IndicConformer Bengali and a 28.6 MB int8 copy of Vosk are more accurate.
Shruti Telugu
Telugu and English · 29.7 MB · 4 November 2026
On Telugu conversations that mix in English, fewer errors than IndicConformer Telugu, a model almost five times its size, and Whisper Telugu fine-tunes up to 32 times its size.
On read Telugu, IndicConformer Telugu, SraVaani-1.0 and the Whisper Telugu fine-tunes are more accurate.
Shruti Hindi · 29.5 MB · Hindi, English and Hinglish · 19 October 2026
100× smaller than OpenAI’s Whisper large-v3, with fewer word errors on the same Hindi test clips.
On the same Hindi test clips, Shruti Hindi makes fewer word errors than Whisper large-v3, a 3,087 MB model: Monsoon 20.5 against 33.3, FLEURS 20.1 against 28.9, Lahaja 22.9 against 31.2. On English, Whisper is clearly better (Indian English 21.4 against 7.4 on the same clips). It is also the smallest open model we know of that does Hindi, English and Hinglish in one file.
At 29.5 MB, Shruti Hindi is about 16× smaller than the Hindi-only models we measured it against, and it writes English words in English inside Hindi, the way people type Hinglish. It runs offline on a budget phone: about 1 second per sentence and 80 MB of memory on a Samsung Galaxy F62 with the native engine. Of the open models we measured, it makes the fewest errors on Hinglish (MUCS 2021, 3,136 clips), including two Whisper models fine-tuned for Hinglish, and it stays ahead when both sides are written in Roman script. On pure Hindi, the larger Hindi-only models are clearly more accurate.
| Model | File size | Monsoon Hindi | FLEURS Hindi | Lahaja (Hindi accents) | MUCS Hinglish | Svarah (Indian English) | LibriSpeech (English) | Words invented on 100 silent clips |
|---|---|---|---|---|---|---|---|---|
| ShrutiUdgam Labs | 29.5 MB (smallest) | 20.46 | 19.92 | 26.28 | 35.21 (best) | 22.47 | 5.95 | 0 (best) |
| Koyal-hi-120MAdalat AI | 481 MB | 11.64 (best) | 9.56 (best) | 18.70 | 57.51 | Hindi only | Hindi only | 0 (best) |
| IndicConformer HindiAI4Bharat | 482 MB | 15.31 | 11.31 | 13.18 (best) | 64.48 | Hindi only | Hindi only | 88 |
| Vosk small (hi + en-in)Alpha Cephei | 139 MB | 35.75 | 18.07 | 26.60 | 61.14 | 38.51 | 30.18 | 1 |
| Whisper-Hindi2Hinglish-SwiftOriserve | 296 MB | 57.16* | n/c | n/c | n/c | 20.16 | 12.60 | 1,676 |
| Whisper-smallOpenAI | 971 MB | 128.25 | 59.42 | 117.5 | – | – | – | – |
| whisper-base-hinglishabhishekgautamm | 290 MB | 65.66* | – | – | 87.05* | 27.11† | 15.53† | 500 |
| whisper-tiny-hinglish-v2abhishekgautamm | 151 MB | 70.60* | – | – | 87.73* | 34.50† | 23.92† | 500 |
| Whisper large-v3OpenAI | 3,087 MB | 33.29 | 28.88 | 31.19‡ | 79.94‡ | 7.39‡ (best) | 2.25‡ (best) | 538 |
Word error rate %, lower is better. Same test sets and the same scorer for every model; Monsoon Hindi with the Hugging Face Hindi leaderboard’s scorer, on the public split. Shruti was run in its on-device engine on a Mac, the other models in the same harness on a GPU or a Mac. Measured 18–19 October 2026.
The best number in each column is in bold. Hindi only: the model does not transcribe English. n/c: not comparable, because the model writes Hindi in Roman letters only. *The model writes Roman script only, so this column mostly measures the script, not the hearing. –: not measured. The silence test uses silent clips only, not noise or music.
†First 1,500 Svarah and first 1,000 LibriSpeech clips; Shruti on the same clips scores 21.35 and 6.36. ‡Whisper large-v3 (fp16 on a Mac GPU, beam 5, language set) on the first 300 Lahaja, Svarah and LibriSpeech clips and the first 600 MUCS clips; Shruti on the same clips scores 22.87, 21.35, 5.76 and 45.3. On Monsoon and FLEURS both ran on every clip; in that run Shruti scored 20.14 on FLEURS (19.92 in the table is the earlier engine build).
Scored with both sides converted to Roman script by the same function, MUCS Hinglish is: Shruti 34.32, whisper-base-hinglish 43.45, whisper-tiny-hinglish-v2 44.94. The whisper-*-hinglish model cards report 28.4 and 32.0 on a 250-clip sample with their author’s own converter, which we did not run.
For context, the Hugging Face Hindi leaderboard publishes these Monsoon word error rates: Whisper large-v3 (1.55B parameters) 28.17, Whisper large-v3-turbo 40.79, Voxtral Mini 3B 22.9, Qwen3-ASR-0.6B 18.13 and IndicConformer-600M 8.47. Shruti’s 20.46 is on the public split, and the board’s own number for it may differ by a few points. An official rank needs a submission, which we have not made.
Shruti Hindi’s technical report
Where it falls short
- Less accurate than larger Hindi-only models on pure Hindi. Koyal-hi-120M and IndicConformer, about 16× larger, make fewer errors on every Hindi test: 9.56% and 11.31% on FLEURS Hindi against Shruti’s 19.92%.
- Weaker on Hindi accents. On Lahaja, IndicConformer makes 13.18% word errors and Shruti 26.28%.
- Hindi comes out in Devanagari only. It does not write Hindi in Roman letters.
- Less accurate than Whisper large-v3 on English: 7.39% against Shruti’s 21.35% on Indian English (Svarah) and 2.25% against 5.76% on LibriSpeech, on the same clips.
- Names it has never heard are spelled by sound. In our own phone test it wrote its name, Shruti, as “सूती” and Udgam Labs as “outgum labs”.
- Far-away or speaker-played audio can throw it. Played from a small computer speaker across a desk, Hinglish was often taken for English; the same clips given as files were transcribed correctly. Speak close to the device.
- Tested on silence, not on noise or music. It invented no words on 100 silent clips.
- Not tested on Windows by us. The engine has a Windows build; we measured on a Mac, Linux, an Android phone and WebAssembly.
- No leaderboard rank. Our Monsoon number is on the public split; we have not made an official submission.
Try Shruti Hindi Shruti Hindi on Hugging Face the model file, the full results and how each model was run
Full Shruti Hindi results: charts, next to Sarvam’s models, on a budget phone, and the model in detail
One small file
Shruti Hindi is a single 29.5 MB file: the whole model, 55M parameters, for three ways of speaking. The Hindi-only models in our comparison are 481 and 482 MB, and Whisper-small is 971 MB. A file this size can ship inside an app or download over a phone connection, and it runs with no server at all.
It is built on Cactus Whistle, an open speech model from Cactus Compute. We fine-tuned all 55M of its weights, added 714 Devanagari vocabulary pieces, and trained it on 2,732 hours of openly licensed Indian speech.
Next to Sarvam’s speech models
Two of Sarvam’s speech-to-text models for Indian languages: Sarvam Edge, which runs on its partners’ devices, and Saaras v4, a paid cloud API. We have not measured either, so this table compares what is published, not accuracy.
| Fact | Shruti | Sarvam Edge speech-to-text | Sarvam Saaras v4 |
|---|---|---|---|
| Availability | Open weights, Apache-2.0 | Closed; commercial partners only | Paid cloud API |
| Size | 29.5 MB file, 55M parameters | About 294 MB (FP16), 74M parameters (Sarvam’s figures) | Server model |
| Internet needed | No: phone, laptop or browser | No, on partner devices | Yes |
| Shown running on | Samsung Galaxy F62 (2021, 6 GB RAM) | Flagship chips (for example Snapdragon 8 Gen 3) in Sarvam’s demos | Servers |
| Languages | Hindi, English, Hinglish | 10 Indian languages | 22 Indian languages and English |
| Published accuracy on shared tests | Yes, on this page | None published | Not measured by us |
Sarvam’s 294 MB is unquantised (16-bit); at 4 bits it would be roughly 37 MB. Saaras v4 is a large cloud model and is likely more accurate than Shruti, and Sarvam Edge is not available to test, so this compares facts, not accuracy.
Sources: Sarvam Edge launch post (14 February 2026) · Sarvam Edge product page · Sarvam model docs (Saaras).
Shruti Hindi on a budget phone
Samsung Galaxy F62: Exynos 9825, 6 GB of memory, Android 13. A five-year-old phone, launched in 2021. Offline, on 2 threads.
- A sentence of about 7 seconds
- ~1 s
- Including loading the model
- A 60-second recording
- 9.5 s
- 6.3× faster than real time
- Peak memory
- 80 MB
- Over the same runs
42 of 51 transcripts were identical to the Mac’s; the rest differ by a letter or two.
- Browser engine (WebAssembly, one thread, run in Node on a Mac)A 9.6 s clip in 0.45 s, with transcripts identical to the native engine
- Hugging Face Space (a shared 2-core CPU)A 2.8 s clip in 0.35 s
The model
- Parameters
- 55M
- File
- 29.5 MB, one .cact file (W4A8: 4-bit weights, 8-bit activations)
- Built on
- Cactus Whistle by Cactus Compute (Apache-2.0). All 55M weights fine-tuned; 714 Devanagari vocabulary pieces added
- Training data
- 2,732 hours of openly licensed Indian speech (see the credits below)
- Languages
- Hindi (in Devanagari), English, and Hinglish with English words in Latin script
- Input
- 16 kHz mono audio of any length: one pass up to 30 s, longer audio in 30 s windows
- Engine
- Cactus needle (Apache-2.0) on Mac, Linux, Windows, Android, iOS and in the browser (WebAssembly). Measured by us on a Mac (Apple silicon), Linux (x86), an Android phone and WebAssembly; not tested by us on Windows
- Licence
- Apache-2.0 (weights), keeping Cactus’s notice
Shruti Marathi · 29.7 MB · Marathi and English · 2 November 2026
The most accurate open Marathi speech-to-text model under 100 MB that we measured.
Shruti Marathi writes Marathi in Devanagari and keeps English words in English, the way people type: उद्या सकाळी नऊ वाजता physics ची exam आहे. Every other open model under 100 MB we measured gets more Marathi words wrong than right. It is within 1.33× of IndicConformer Marathi’s error rate on FLEURS (29.9 against 22.4) at about a fifth of its size, and on conversations that mix in English it makes fewer errors than that model when English words are written in English. It runs offline on a five-year-old phone, 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 | FLEURS | Kathbath | DiarBench | IndicVoices | SPRING-INX | Vaani |
|---|---|---|---|---|---|---|---|
| Shruti Marathi | 29.7 MB | 29.9 | 24.5 | 38.2 | 22.2 | 42.9 | 32.2 |
| Whisper tiny | 44 MB | 273.1 | 278.1 | 373.9 | 321.8 | 375.6 | 338.7 |
| Whisper base | 82 MB | 177.9 | 193.2 | 402.9 | 450.2 | 420.6 | 412.3 |
| marathi-conformer-33m-moe | 136.7 MB | 41.0 | 32.2 | 76.7 | 66.0 | 77.3 | 64.0 |
| IndicConformer Marathi | 137.7 MB | 22.4 | 14.1 | 41.5 | 27.6 | 53.0 | 44.0 |
Word error rate %, lower is better; 200 clips per set, the same scorer for every model, measured 30 October to 2 November 2026. FLEURS and Kathbath are read Marathi; the other four are conversations that mix in English, scored with English words written in English. With the English words dropped from those references, IndicConformer Marathi is ahead (DiarBench 32.3 against 40.9). Whisper tiny and base add words, so their rates pass 100%.
Where it falls short
- On pure Marathi, IndicConformer Marathi (about 5× larger) makes about a quarter fewer errors on FLEURS and about 40% fewer on Kathbath.
- Spelling variants (उशिरा/उशीरा) and joined words count as errors and are common; some English loanwords come out in Devanagari.
- It does not do Hindi: pick Hindi above for Shruti Hindi.
- Noise, music and speaker-played audio were not tested.
Try Shruti Marathi Shruti Marathi on Hugging Face the model file, the full results and how each model was run
Shruti Tamil · 29.7 MB · Tamil and English · 3 November 2026
The most accurate open Tamil speech-to-text model under 100 MB that we measured.
Shruti Tamil writes Tamil in Tamil script and keeps English words in English, the way people type: கல்யாணத்துக்கு catering order confirm பண்ணிட்டேன். Every other open model under 100 MB we measured gets more Tamil words wrong than right. On conversations that mix in English it makes fewer errors than IndicConformer Tamil, about five times its size, when English words are written in English (DiarBench 52.5 against 58.7). It runs offline on a five-year-old phone, 10.8× faster than real time in 64 MB of memory with the native engine, and it invented no words on 100 silent clips.
| Model | File | FLEURS | Kathbath | DiarBench |
|---|---|---|---|---|
| Shruti Tamil | 29.7 MB | 38.5 | 33.2 | 52.5 |
| Whisper tiny | 43.5 MB | 226.7 | 239.6 | 244.8 |
| Whisper base | 81.8 MB | 124.5 | 108.8 | 152.5 |
| Thedal v11 (non-commercial) | 102.6 MB | 42.2 | 38.1 | 70.1 |
| IndicConformer Tamil | 137.7 MB | 27.8 | 25.0 | 58.7 |
| deepdml whisper-base-ta | 290.4 MB | 38.7 | 39.1 | 81.1 |
Word error rate %, lower is better; 200 clips per set, the same scorer for every model, measured 2 November 2026. FLEURS and Kathbath are read Tamil; DiarBench is conversation that mixes in English, scored with English words written in English. With the English words dropped from the reference, IndicConformer Tamil is ahead (51.4 against 62.2). On FLEURS, deepdml’s whisper-base-ta (290 MB as published) is level with Shruti Tamil. Whisper adds words, so its rates pass 100%.
Where it falls short
- On pure Tamil, IndicConformer Tamil (about 5× larger) makes about 28% fewer errors on FLEURS and 25% fewer on Kathbath.
- Nearby number words can be swapped (நூத்தம்பது heard as மூத்தம்பது), and some English loanwords come out in Tamil script.
- Language detection can pick English for Tamil speech with many English words.
- Noise, music and speaker-played audio were not tested.
Try Shruti Tamil Shruti Tamil on Hugging Face the model file, the full results and how each model was run
Shruti Bengali · 29.7 MB · Bengali and English · 3 November 2026
On conversations that mix in English, fewer errors than Bengali models three and five times its size.
Shruti Bengali writes Bengali in Bengali script and keeps English words in English, the way people type: বাচ্চাদের রবীন্দ্রসঙ্গীতের rehearsal শনিবার. On real conversations that mix in English, scored with English words written in English, it makes fewer errors than Vosk Bengali (90 MB) and IndicConformer Bengali (138 MB): DiarBench 36.0 against 42.8 and 39.3. It writes about half of the English words in English letters; both of those models write none. It runs offline on a five-year-old phone, 12.6× faster than real time in 64 MB of memory with the native engine, and it invented no words on 100 silent clips.
| Model | File | DiarBench | FLEURS | Kathbath |
|---|---|---|---|---|
| Shruti Bengali | 29.7 MB | 36.0 | 29.9 | 22.2 |
| Whisper tiny | 43.5 MB | 540.9 | 361.6 | 403.7 |
| Whisper base | 81.8 MB | 339.9 | 176.7 | 214.5 |
| Vosk Bengali int8 (third-party copy) | 28.6 MB | 43.3 | 20.9 | 22.4 |
| Vosk Bengali (Zipformer) | 90.0 MB | 42.8 | 20.8 | 21.7 |
| Dolphin-base int8 | 103.7 MB | 93.0 | 41.1 | 45.9 |
| IndicConformer Bengali | 137.7 MB | 39.3 | 20.7 | 12.1 |
Word error rate %, lower is better; 200 clips per set, the same scorer for every model, measured 2 November 2026. DiarBench is conversation that mixes in English, scored with English words written in English; FLEURS and Kathbath are read Bengali. With the English words dropped from the DiarBench reference, both larger models are ahead (34.8 and 38.5 against 41.8). SraVaani-1.0 (909 MB) is ahead on every set (DiarBench 34.6). Whisper adds words, so its rates pass 100%.
Where it falls short
- On read Bengali, Vosk Bengali and IndicConformer Bengali are clearly more accurate (FLEURS 20.8 and 20.7 against 29.9), and so is a 28.6 MB int8 copy of Vosk Bengali (20.9), slightly smaller than Shruti Bengali.
- Some English words come out in Bengali script (derby as ডার্ভিটা), and spelling variants count as errors.
- Noise, music and speaker-played audio were not tested.
Try Shruti Bengali Shruti Bengali on Hugging Face the model file, the full results and how each model was run
Shruti Telugu · 29.7 MB · Telugu and English · 4 November 2026
On Telugu conversations that mix in English, fewer errors than IndicConformer Telugu, a model almost five times its size, and Whisper Telugu fine-tunes up to 32 times its size.
Shruti Telugu writes Telugu in Telugu script and keeps English words in English, the way people type: హైదరాబాద్లో కొత్త company నుంచి offer letter వచ్చింది. On real Telugu conversations that mix in English, scored with English words written in English, it makes fewer errors than IndicConformer Telugu (138 MB) and the Whisper-small Telugu fine-tune (967 MB): DiarBench 45.4 against 52.9 and 55.7. On those conversations it is level with SraVaani-1.0, a 909 MB model. It writes about half of the English words in English letters (53.7%); IndicConformer Telugu, Vosk Telugu and the Whisper Telugu fine-tunes write none. It makes about half the errors of Vosk Telugu (60.5 MB) on every test we ran. It runs offline on a five-year-old phone, about 10× faster than real time in 64 MB of memory with the native engine, and it invented no words on 100 silent clips.
| Model | File | DiarBench | FLEURS | Kathbath |
|---|---|---|---|---|
| Shruti Telugu | 29.7 MB | 45.4 | 38.0 | 32.9 |
| Whisper tiny | 43.5 MB | 659.1 | 687.8 | 583.3 |
| Vosk Telugu (small) | 60.5 MB | 93.8 | 77.1 | 80.1 |
| Whisper base | 81.8 MB | 371.3 | 220.1 | 363.3 |
| Dolphin-base int8 | 103.7 MB | 86.9 | 73.4 | 66.2 |
| IndicConformer Telugu | 137.7 MB | 52.9 | 24.5 | 23.0 |
| Whisper-tiny Telugu fine-tune (vasista22) | 151.1 MB | 59.2 | 34.2 | 34.4 |
| Dolphin-small int8 | 249.7 MB | 98.0 | 60.9 | 52.6 |
| Whisper small | 264.5 MB | 201.1 | 169.7 | 154.1 |
| Whisper-base Telugu fine-tune (vasista22) | 290.5 MB | 55.3 | 28.9 | 29.5 |
| SraVaani-1.0 | 908.8 MB | 47.8 | 22.0 | 20.3 |
| Whisper-small Telugu fine-tune (vasista22) | 967.1 MB | 55.7 | 24.0 | 26.0 |
Word error rate %, lower is better; 200 clips per set, the same scorer for every model, measured 2 November 2026. DiarBench is real conversation that mixes in English, held out for every model, scored with English words written in English; FLEURS and Kathbath are read Telugu. On DiarBench the gaps to IndicConformer Telugu and the Whisper Telugu fine-tunes hold in a paired bootstrap; against SraVaani-1.0 the interval includes zero, so the two are level. Whisper adds words, so its rates pass 100%.
Where it falls short
- On read Telugu, IndicConformer Telugu (about 5× larger) makes about 36% fewer errors on FLEURS (24.5 against 38.0) and 30% fewer on Kathbath (23.0 against 32.9). SraVaani-1.0 (about 30× larger) is ahead on every read set, and the Whisper-tiny Telugu fine-tune, published at 151 MB but about 44 MB as a whisper.cpp q8_0 copy, is ahead on FLEURS (34.2) and level on Kathbath.
- On conversations scored against the native reference, which drops the English words, most larger models are ahead (SraVaani-1.0 33.0, IndicConformer Telugu 37.3, Shruti Telugu 58.0): Shruti keeps English words in English.
- Some English words come out in Telugu script (online as ఆన్లైన్లో), and joined words and spelling variants count as errors.
- No punctuation, and numbers come out as words. Noise, music, far-field and speaker-played audio were not tested.
Try Shruti Telugu Shruti Telugu on Hugging Face the model file, the full results and how each model was run
Good fits
- Voice input in apps where the audio should stay on the device.
- Dictation, notes and search in any Shruti language, with English words kept in English.
- Phones with little memory, and places with a weak connection or none.
- Live text from a microphone, with the engine’s streaming calls.
Where each model falls short is in its own section above.
The name
Shruti
श्रुति
Shruti (श्रुति) is Sanskrit for “that which is heard”.
Small models that listen, on your device.
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: one file per language, from its Hugging Face repo
# Shruti Hindi: shruti.cact
# Shruti Marathi: shruti-marathi.cact
# Shruti Tamil: shruti-tamil.cact
# Shruti Bengali: shruti-bengali.cact
# Shruti Telugu: shruti-telugu.cact
./needle --model shruti.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.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.
From an AI agent
Shruti Hindi also runs as a tool on our MCP server, so Claude Code, Codex, Cursor and other MCP clients can call it. The agent sends a link to the audio; the model’s Hugging Face Space downloads it and returns the transcript. To keep audio on your own device, use the engine or the demo on this page.
# Claude Code
claude mcp add --transport http udgamlabs https://mcp.udgamlabs.com/mcp
# Codex
codex mcp add udgamlabs --url https://mcp.udgamlabs.com/mcp
# Cursor: .cursor/mcp.json
{ "mcpServers": { "udgamlabs": { "url": "https://mcp.udgamlabs.com/mcp" } } }The tool is shruti_transcribe; the same server has every model that runs as a tool (all tools, and setup for Claude, VS Code and other apps). The model runs on a shared free CPU on Hugging Face, so the first call after a quiet spell waits while it starts.
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 Hindi learned from these openly licensed speech datasets, all of which allow commercial use; each other language’s model card on Hugging Face lists its own:
- AI4Bharat IndicVoicesCC-BY-4.0
- ARTPARK-IISc VaaniCC-BY-4.0
- AI4Bharat ShrutilipiCC-BY-4.0
- AI4Bharat NPTELCC-BY-4.0
- AI4Bharat KathbathCC-BY-4.0
- Mozilla Common Voice 17: English, India and South Asia accentsCC0
- LibriSpeechCC-BY-4.0
- MUCS 2021 Hinglish, via dianavdavidson/MUCS-HinglishCC-BY-4.0 on the dataset card; the original is CC-BY-SA-4.0
- AI4Bharat Rural_Women_ASR_v2CC-BY-4.0
- Google FLEURS, Hindi train splitCC-BY-4.0
Weights and links
- All Shruti models
The Hugging Face collection: every language, with the Space
- Hugging Face Space
One demo for every language, on a server CPU
- Shruti on GitHub
Runnable examples (Python, command line, a web page you can host), checksums and the full comparisons
- Shruti Hindi on Hugging Face
The model file (shruti.cact) and model card
- Shruti Marathi on Hugging Face
The model file (shruti-marathi.cact) and model card
- Shruti Tamil on Hugging Face
The model file (shruti-tamil.cact) and model card
- Shruti Bengali on Hugging Face
The model file (shruti-bengali.cact) and model card
- Shruti Telugu on Hugging Face
The model file (shruti-telugu.cact) and model card
- Cactus needle engines
Prebuilt engines for each platform, and the WebAssembly build
- Cactus Whistle
The speech model every Shruti model is built on
- needle on GitHub
The engine’s source and documentation
Every Shruti model’s weights are released under Apache-2.0, built on Cactus Whistle (Apache-2.0, Cactus Compute). Each model card lists its training datasets and their licences.