Comparison
Real-time streaming tuned for developers, routed through proprietary cloud endpoints your codebase may not be allowed to touch.
Aqua Voice is a real-time, streaming voice-to-text editor powered by its proprietary hosted “Avalon” model. It targets developers and technical professionals by allowing users to edit and rewrite code or text by voice as they speak.
Streams low-latency audio deltas to proprietary cloud endpoints. The Avalon model handles live word-by-word streaming and arbitrary in-line text manipulation commands (e.g., “replace that last function”).
Audio streams and document context are processed on external servers, raising compliance blockers for proprietary codebases.
No option for a permanent local license; recurring fees compound over time.
Lacks an integrated cognitive layer; it cannot answer questions from your past voice notes or autonomously trigger multi-step system actions.
Starter is free for 1,000 words (one-time evaluation); Pro is $8/month billed annually ($96/year) or $10–$12/month month-to-month; Max runs $24/month ($288/year).
Unlimited dictation, free forever. Plus is $6/month or $49/year; Pro is $14/month or $119/year.
See full pricingTyne avoids cloud risk by running acoustic decoding (WhisperKit on the ANE) and semantic processing (Qwen on Metal) directly on your device. Tyne also goes beyond document typing: it integrates native Model Context Protocol servers and Apple EventKit to turn verbal thoughts into scheduled actions and Linear issues.