Kaldi vs Superwhisper

Kaldi is a free, open-source C++ toolkit for speech recognition aimed at researchers and professionals. Its code and scripts cover methods including linear transforms, MMI, boosted MMI, MCE discriminative training and feature-space discriminative training. The toolkit integrates finite-state transducers through OpenFst and includes a matrix library that wraps standard BLAS and LAPACK routines. Example recipes support building speech recognition systems, and downloadable model archives cover speech recognition, speaker identification, speech activity detection, diarization and language modeling. The models may be used for any purpose. Kaldi is released under Apache License 2.0, which permits commercial use and redistribution. It runs on Linux distributions and Mac OS X, supports Android cross-compilation, and can be compiled to WebAssembly for browser execution. Windows compatibility is not actively maintained, and example scripts do not work there. Users obtain the current development version by cloning the GitHub repository and following its INSTALL file. Documentation is expert-oriented; the project directs help requests to its mailing list and bug reports or feature requests to GitHub issues.

Superwhisper turns speech into formatted text for use across applications. Its Super Mode reads the screen and adjusts dictated text to the current app, for example treating email as a message or coding prompts technically. It supports more than 100 languages, automatic language detection, and translation between languages. On-device speech models process audio locally, work without internet, and keep audio off the device's outbound path. With cloud models, audio and text pass through the Superwhisper proxy to the provider; the product says they are not retained for training. It works wherever text can be entered and names Slack, Cursor, and Notion, with coding plugins for Claude Code, OpenCode, Codex, and Pi. A CLI can search and export transcripts, report recording statistics, and start a local MCP server. Free includes voice-to-text, meeting recording and transcription, and email support. Pro costs $8.49 per month or $84.99 per year and adds audio and video transcription, cloud and local models, custom API keys, and priority support. Pro features can be tried for 3,000 words before free-tier features remain available.