introducing rumik oss 1 india's first state of the art open source, fully pre-trained voice model capable of speaking 20+ languages trained on only 66k hours of data, it beats even the top closed models on multiple benchmarks including emotion realism weights are now live 👇🏻

rumik oss 1 is a 3 billion parameter open weights text to speech model it can speak in indian english, hindi, telugu, tamil, kannada, bengali, punjabi and switches between them mid-sentence, and takes delivery instructions in plain text full research blog - download the weights on hugging face -

describe how you want the model to sound like, and it will follow those instructions here are some examples 👇🏻

along with the model, we are also open sourcing two of our internal benchmarks 1. indic-emo this benchmark tests can a model hold an emotion through code-switched speech? 100 prompts, each mixing two to five of our seven languages, equal coverage of happy, sad, angry, excited and professional. three judge models score anonymized clips on a five-point rubric covering tone, dynamics, phrasing and sustained expression. rumik oss 1 comfortably beats @cartesia, @ElevenLabs and only @GeminiApp is better and by a big margin it was expected given gemini 3.1 flash tts must be trained on 1000x more data compared to rumik oss 1 is only trained on 66k hours in total

2. nova this benchmark measures precise delivery of emotions for eg - if you ask for a laugh at word seven, does it land at word seven? 149 english prompts, one vocalization each at a specified word position, seven systems, three synthesis runs. three detectors check position-correct rendering. benchmark + protocol ->

on WER (word error rate) and CER (character error rate) rumik oss 1 tops odia, konkani, maithili while comes second in assamese, kannada, nepali, malyalam

rumik oss 1 comes with CC BY-NC 4.0 license plus an acceptable use addendum. that makes it open weights for research and non-commercial use, speech research, benchmarking, teaching, finetuning for experiments. you can share the weights and your adaptations under the same terms, keeping attribution, license links and a note of what you changed.

congrats to the @rumik_ai team. looks like a good first attempt. hope to see rapid iterations.

@rumik_ai thanks a ton @soumithchintala

LFG🔥🔥

You will win 🍀

Congratulations 🎊

I was using @SarvamAI, let's see how this plays out.

@SarvamAI let's go

Congratulations, how can we contribute?

Spread the word 🤌

I'll make sure to cover each update from now 🙌

hahaha indeed

took you guys long enough

Great move to open source it 💪 We should add them to @indos_tech catalog @utkarsh_k1c

Great I am happy india is taking root in ai landscape

Crazy! Excited to try it out!!

lmk how it goes!

super cool, congratulations on the release!

thanks @thepushkarp

never not impressed by rumik. so so good 🙌

if it really beats top closed models, it could shift the landscape for accessibility

very cool, congrats!

tahnks @himanshustwts

🚀🚀🚀🚀

training on just 66k hours and outperforming top models is no small feat

Congratulations 🎉. Is Bengali trained as well?

Yes

very cool, congrats on the launch!

never bet against these guys @lets_dig_deeper and @bhartivatsal ❤️

It's exciting to know that we have multiple options across different languages, which can now be used as an alternative to Google's live models. Though at this point in time, I would still prefer using Gemini Live because I feel I can make it sound better in Tamil and have the same expressiveness that has been demonstrated here. I am really excited to try this on the next version, though!

Congrats for the launch

does it support Santali?

insane🔥, and well detailed blog!

Let's go congrats for the crazy feat

66k hours and these benchmark results is seriously impressive. Great work.🤌

Incredible timing, I just spent half a day messing with Sarvam to make it sound right. Congrats!

This is the first indian AI thing that is actually superior to the other peer products.........I dont know how well it is compared to GPT Live (Its the current SOTA I think), But certainly one of the better open source models from the demos I have seen.

yooo that's insane!! congrats!!

Languages are finally becoming our strength

W

from Rohan to another....keep at it bro...naam roshan karo humara.

Lfggggg