TypeWhisper/typewhisper-mac v1.3.0-rc1

on GitHub

TypeWhisper 1.3.0-rc1 opens the 1.3 release-candidate line. The release adds spoken feedback, per-request STT control through the HTTP API and CLI, multilingual language hints, and the new plugin-compatibility safeguards introduced after #327, on top of a set of hotkey, audio, and plugin reliability fixes.

New Features

• Spoken feedback (text-to-speech) with a new System Voice marketplace plugin that uses the built-in macOS AVSpeechSynthesizer voices. Voice and speed are configurable in the settings, and the feedback is scoped to transcription readback only.
• Per-request STT engine and model selection through the HTTP API (engine/model on /v1/transcribe) and the CLI (typewhisper transcribe --engine <id> --model <id>). When omitted, the active profile defaults are used.
• Multilingual language hints with a multi-select picker, inline search, and a selected-count indicator, wired through to the transcription providers.

Bug Fixes

• Restored GPT-5 and Codex compatibility for the bundled OpenAI plugin.
• Fixed Fn-hotkey handling so both press-and-release and press-and-hold strategies work reliably.
• Spoken feedback is now limited to transcription readback and no longer narrates unrelated UI events.
• Addressed the 1.2.3 review blockers (K1-K4, M1, M7, M8) in the release pipeline and plugin registry.
• Split the marketplace into legacy and v1 feeds, moved plugin and term-pack fetches out of startup, and hardened plugin loading so incompatible external bundles are skipped instead of breaking launch.
• Hardened audio recovery during Bluetooth route changes to avoid crashes.
• Dictionary terms are forwarded through the streaming providers (AssemblyAI, Soniox, SpeechAnalyzer) without breaking the live session.

Other Changes

• Refactored the Qwen3 context-bias formatter for cleaner prompt injection and easier future tuning.
• Incremental live transcription, Google Cloud STT release mapping, and the multi-release plugin registry are carried forward from the late 1.2.x work.
• All current marketplace plugins now have v1 releases for the RC line, including System Voice as an installable TTS plugin.