v0.5.4 Release Notes

Released 2026-09-03

v0.5.3 -> v0.5.4

Summary

Gives the router a voice layer with speech-to-text and text-to-speech agents implemented for OpenAI and Gemini behind a shared audio contract. Model discovery gains matching capability filters so callers can list what each direction actually supports.

翻譯

為 router 補上語音層，以共用的音訊契約提供語音轉文字與文字轉語音代理，並在 OpenAI 與 Gemini 上實作。模型探索同步新增對應的能力過濾，讓呼叫端能列出各方向實際支援的模型。

Changes

FEAT

Add STTAgent and TTSAgent with OpenAI and Gemini implementations returning WAV audio (@pardnchiu) [7bf7640]
Add STTOnly and TTSOnly model filters with speech capability detection (@pardnchiu) [7bf7640]

翻譯

新增 STTAgent 與 TTSAgent，並實作 OpenAI 與 Gemini 版本，統一輸出 WAV 音訊
新增 STTOnly 與 TTSOnly 模型過濾選項及語音能力判別

Scope

core/ — FEAT (audio.go, reasoning.go)
core/openai/ — FEAT (audio.go, models.go)
core/gemini/ — FEAT (audio.go, models.go)

Generated by SKILL