Direction
Roadmap
Product direction for Tojito — goals and capabilities under development, not guaranteed delivery dates.
This page describes where Tojito is headed. Items under “coming next” are product direction, not commitments with dates. Capabilities move here only when they are ready to ship.
Available now
Where the engine is today
Early desktop capabilities already in the product.
Real-time local audio processing
Process desktop audio streams on-device with low latency. Your audio stays on your machine.
Offline profanity filtering
Privacy-first filtering that runs locally — no cloud round-trip for your audio.
English profanity filtering
Production-ready English filtering for live streams and recordings.
Russian profanity support
Russian filtering where currently implemented and tested. Coverage continues to expand.
Coming next
Coming next
Broader platform ideas under development. These are goals, not available features.
High-quality multilingual speech recognition
Broader language coverage and stronger recognition quality offline.
Offline speech translation
Translate speech locally without sending audio to the cloud.
Real-time voice translation & TTS
Live voice translation and speech synthesis as the engine matures.
Live captions
On-device captions for streams, calls, and recordings.
Semantic content filtering
Policy-aware filtering beyond keyword and profanity matching.
Audio enhancement
Clarity, noise, and voice quality improvements powered by local models.
Additional languages & policies
More languages, dialects, and configurable filtering policies.