Free ASR is a zero-dependency, pure-Swift real-time streaming speech-to-text client and complete protocol specification, reverse-engineered from Doubao Input Method for macOS. It documents what the gateway actually validates and what it does not.
Be the first to rate Free ASR. Your feedback helps other users decide.
A pure-Swift client for the streaming ASR WebSocket gateway, which works without signing into an account.
The repository documents how authentication and streaming work, including which fields the server checks and which it ignores.
Any randomly generated 16-digit numeric string is accepted; the server uses device_id only for rate-limiting buckets and log tracing.
Similar tools in the same category — compare side-by-side
ESP32 Pie ASR runs live English speech recognition on an ESP32-P4: a 65.7M-parameter streaming Zipfo...
ElevenLabs is an AI voice platform for generating lifelike speech and cloning voices. It covers 128 ...
Whisper is OpenAI's open-source speech-to-text model. It transcribes 90+ languages and outputs punct...
Guides and comparisons about audio tools
Eight single-purpose AI tools that picked one narrow job and finished it: on-chip speech recognition, Threads scheduling, stunt videos, HS codes and interviews.
How remixers actually use AI audio tools: stem separation first, generation second, mastering last, with the real limits of each tool in the chain.
A realistic look at AI background music tools in 2026: Suno, Soundraw, Beatoven, Mubert, and Epidemic Sound — and where licensing gets tricky.
Transform your radio production with AI audio tools. From voice generation to noise removal, discover how AI is revolutionizing radio broadcasting in 2026.
A start-to-finish AI podcast workflow: scripting, recording, editing, show notes, and publishing — with honest tool picks and limits for every stage in 2026.
