An Android app that runs offline on low-power phones to convert speech to text and text to speech in ten Indian languages, transmitting it over local Wi-Fi or Bluetooth.
Indian Space Research Organisation(ISRO) · Department of Space / Indian Space Research Organisation · Software
Signing in saves it for your whole team, so everyone on your invite link sees the same two entries. Anything you shortlisted while signed out comes with you.
Decomposed from what the description asks for. Nothing added.
Android App Interface
A mobile application built to run on low and mid-range Android devices with local audio capture and playback.
Local STT Module
An offline speech-to-text pipeline supporting ten specified Indian languages using open-source machine learning frameworks.
Local TTS Module
An offline text-to-speech pipeline that converts received text into intelligible speech and alert messages.
Local Transmission Link
A module that streams data between devices using Wi-Fi or Bluetooth with minimal latency.
Both columns are read off the brief's own wording. Nothing here is inferred from the ministry's name.
The evaluators will check model and app size, RAM footprint, CPU usage, Word Error Rate for STT, human legibility for TTS, and latency metrics including Real Time Factor. They will strictly verify that the solution uses only open-source frameworks and runs fully offline without internet APIs.
A jury can still ask about these. Decide them deliberately rather than by accident.
Generated from the brief's own wording and the competition's published rules, never from a guess about what this ministry prefers.
Specific target numbers for maximum app size or RAM footprint?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Exact maximum acceptable latency in milliseconds?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Target Word Error Rate percentage for success?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Has any part of this been shown at a previous event, hackathon or college project?
The guidelines are explicit: your solution must not have appeared in any previous event or programme, of any sort. A recycled project is what a team under time pressure reaches for.
The brief asks for android app interface. How would you build that?
Decoded from SIH26173 itself: A mobile application built to run on low and mid-range Android devices with local audio capture and playback. The brief asks for it by name.
The brief asks for local stt module. How would you build that?
Decoded from SIH26173 itself: An offline speech-to-text pipeline supporting ten specified Indian languages using open-source machine learning frameworks. The brief asks for it by name.
The brief asks for local tts module. How would you build that?
Decoded from SIH26173 itself: An offline text-to-speech pipeline that converts received text into intelligible speech and alert messages. The brief asks for it by name.
The brief asks for local transmission link. How would you build that?
Decoded from SIH26173 itself: A module that streams data between devices using Wi-Fi or Bluetooth with minimal latency. The brief asks for it by name.
Where does your data come from: a published source, one you collect, or one you generate?
No dataset is attached to this problem statement, so sourcing it is part of the work and nobody told you that.
Why not use what already exists? Name the closest thing to this that is already running.
A team that has not named the alternative themselves is answering this for the first time in the room.
Which single thing will you demonstrate end to end, start to finish, with nothing skipped?
Ours, not a rule: a narrow thing that fully works survives questioning better than a broad thing that half works. If nobody on the team can name it, that is the finding.
Show me this working: the evaluators will check model and app size, RAM footprint, CPU usage, Word Error Rate for STT, human legibility for TTS, and latency metrics including Real Time Factor.
This is the evaluator read for your problem statement, decoded from the brief's own wording.
Show me this working: they will strictly verify that the solution uses only open-source frameworks and runs fully offline without internet APIs.
This is the evaluator read for your problem statement, decoded from the brief's own wording.
Each one is quoted from a gap in the brief, not a guess about your team.
No measurable target
The text lists evaluation criteria like low Word Error Rate and minimal latency, but never states exact numeric thresholds required to pass.
What the organisers attached, and what the brief assumes you can get.
Same organisation, same year. Reading two of theirs tells you more about what they care about than reading one.