Skip to content

Commit d79c02f

Browse files
author
Xu Yun
committed
chore: release v0.10.0
1 parent 2c736cc commit d79c02f

18 files changed

Lines changed: 825 additions & 126 deletions

File tree

CHANGELOG.md

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,25 @@ All notable changes to this project will be documented in this file.
44

55
The format is based on [Keep a Changelog](https://keepachangelog.com/), and this project adheres to [Semantic Versioning](https://semver.org/).
66

7+
## [0.10.0] - 2026-04-26
8+
9+
### Added
10+
- **StepAudio 2.5 ASR** — added StepFun batch transcription via HTTP + SSE, including API key/model settings, provider selection, history metadata, and re-transcription support.
11+
- **Per-app text injection overrides** — Input Settings can now remember recent target apps and choose pasteboard or typing mode per application, so apps with special editor behavior can use their own injection strategy.
12+
- **LLM connectivity test** — Settings → LLM can send a real correction probe with the active provider and model, then show status, response time, test input, and model output.
13+
- **History replay injection test** — saved recordings can now be re-transcribed, post-processed, and injected into the current foreground app for end-to-end provider and injection checks.
14+
15+
### Changed
16+
- Expanded VoiceX from eleven to twelve ASR backends.
17+
- Re-transcription now returns the final post-processed text in addition to ASR and LLM intermediate results, and it respects the original history mode when choosing assistant vs. translation prompts.
18+
- Clipboard injection and macOS paste shortcuts now use steadier timing to improve reliability in editors that process paste events slowly.
19+
- The compact HUD now keeps the processing intent chip visible during batch and compact states.
20+
21+
### Fixed
22+
- Prevented the HUD from stealing input focus and preserved the original foreground app context when recording starts.
23+
- Hardened hotkey session races around rapid start/stop/cancel flows.
24+
- Empty Qwen sessions that exit because of silence are now handled without leaving stale session state.
25+
726
## [0.9.5] - 2026-04-09
827

928
### Changed

README.en.md

Lines changed: 10 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -19,8 +19,8 @@ VoiceX is a cross-platform desktop voice input tool. Its overall pipeline is: re
1919
- **One hotkey, multiple gestures** — a single global hotkey drives three interaction modes: tap for hands-free dictation, hold for push-to-talk, double-tap to translate.
2020
- **Real-time HUD overlay** — a lightweight always-on-top display shows live transcription, recording mode, countdown timer, and processing status, and on macOS it follows the active Space when triggered from another desktop.
2121
- **LLM-powered post-processing** — optionally send ASR output through an LLM for correction, translation, or refinement, with customizable prompt templates and dictionary-aware context.
22-
- **Smart text injection** — recognized text is pasted into the active app via clipboard (with automatic backup/restore) or simulated typing, seamlessly.
23-
- **History & statistics** — every dictation is logged with full metadata (duration, device, ASR/LLM model, original vs. corrected text), browsable by date with audio playback and re-transcription.
22+
- **Smart text injection** — recognized text is pasted into the active app via clipboard (with automatic backup/restore) or simulated typing, with per-app overrides for apps that need a different injection strategy.
23+
- **History & statistics** — every dictation is logged with full metadata (duration, device, ASR/LLM model, original vs. corrected text), browsable by date with audio playback, re-transcription, and replay injection testing.
2424
- **Cross-device sync** — a self-hosted sync server keeps history in sync across your machines.
2525

2626
## Interaction Modes
@@ -73,6 +73,7 @@ Features:
7373
- **ASR correction** — fix recognition errors using dictionary context and customizable prompts.
7474
- **Translation** — translate dictation to English, triggered by double-tap gesture.
7575
- **Prompt templates** — full control over correction and translation prompts, with `{{DICTIONARY}}` placeholder for hot-word injection.
76+
- **Connectivity test** — send one real correction request with the active provider and model to inspect latency and output quality.
7677

7778
## Dictionary & Hot-Words
7879

@@ -85,11 +86,17 @@ Features:
8586
- **Smart punctuation cleanup** — auto-remove trailing punctuation from short sentences (configurable threshold).
8687
- **Keyword substitution** — regex/exact/contains replacement rules applied before text injection.
8788

89+
## Text Injection
90+
91+
- Global support for clipboard paste and simulated typing modes.
92+
- Per-app overrides can be created from recent target apps, so standard text fields can keep clipboard paste while editors that are sensitive to paste events can switch to typing.
93+
- On macOS, VoiceX records the target app when the hotkey starts, reducing the chance that the HUD or main window changes the injection target.
94+
8895
## History & Statistics
8996

9097
- Full history grouped by date, with per-record audio playback, copy, and detail view.
9198
- Side-by-side comparison of original ASR output vs. LLM-corrected text.
92-
- Re-transcribe any saved recording with a different ASR backend and optional LLM correction to compare providers on the same audio.
99+
- Re-transcribe any saved recording with a different ASR backend and optional LLM correction to compare providers on the same audio; replay the final text into the current app to test the full end-to-end flow.
93100
- Failed batch transcriptions are preserved locally with the original audio so you can retry later instead of repeating the whole dictation immediately.
94101
- Configurable retention policies for text and audio (7 / 30 / 180 / 365 days, or forever).
95102
- Overview dashboard: total duration, character count, AI correction calls, average dictation speed — aggregated per device.

README.md

Lines changed: 10 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -19,8 +19,8 @@ VoiceX 是一个跨平台桌面语音输入工具。整体处理链路为:录
1919
- **一键多用** — 单个全局热键驱动三种交互模式:轻点启动免提听写、长按进入按住说话、双击触发翻译。
2020
- **实时 HUD 浮层** — 轻量置顶窗口,实时显示转写文本、录音模式、倒计时和处理状态;在 macOS 多桌面场景下也会跟随当前活跃 Space 显示,不打断当前工作流。
2121
- **LLM 后处理** — 可选将 ASR 输出交给大模型做纠错、翻译或润色,支持自定义 prompt 模板和词典上下文注入。
22-
- **智能文本注入** — 识别结果通过剪贴板粘贴(自动备份/恢复原内容)或模拟键入送入当前应用,无缝衔接
23-
- **历史记录与统计** — 每次听写保留完整元数据(时长、设备、ASR/LLM 模型、原文 vs. 纠正文本),按日期浏览,并支持录音回放与重新转录
22+
- **智能文本注入** — 识别结果通过剪贴板粘贴(自动备份/恢复原内容)或模拟键入送入当前应用,并可按目标应用单独指定注入方式
23+
- **历史记录与统计** — 每次听写保留完整元数据(时长、设备、ASR/LLM 模型、原文 vs. 纠正文本),按日期浏览,并支持录音回放、重新转录和重放注入测试
2424
- **跨设备同步** — 自建同步服务器,在多台设备间保持历史一致。
2525

2626
## 交互模式
@@ -73,6 +73,7 @@ VoiceX 可选将 ASR 输出交给 LLM 做纠错或翻译。支持的提供商:
7373
- **ASR 纠错** — 结合词典上下文和可自定义 prompt 修正识别错误。
7474
- **翻译** — 将听写内容翻译为英文,由双击手势触发。
7575
- **Prompt 模板** — 完全自定义纠错和翻译 prompt,支持 `{{DICTIONARY}}` 占位符注入热词。
76+
- **连通性测试** — 使用当前 provider 和模型发起一次真实纠错请求,检查响应时间和输出质量。
7677

7778
## 词典与热词
7879

@@ -85,11 +86,17 @@ VoiceX 可选将 ASR 输出交给 LLM 做纠错或翻译。支持的提供商:
8586
- **智能标点清理** — 短句自动去除末尾标点(阈值可配置)。
8687
- **关键词替换** — 正则/精确/包含替换规则,在文本注入前执行。
8788

89+
## 文本注入
90+
91+
- 全局支持剪贴板粘贴和模拟键入两种注入方式。
92+
- 可按最近使用的目标应用设置覆盖规则,例如在普通文本框中使用剪贴板粘贴,在对粘贴事件敏感的编辑器中改用模拟键入。
93+
- macOS 上会在热键开始时记录目标应用,降低 HUD 或主窗口抢焦点对注入目标的影响。
94+
8895
## 历史记录与统计
8996

9097
- 全量历史按日期分组,每条记录支持录音回放、复制和详情查看。
9198
- 原始 ASR 输出与 LLM 纠正结果的并排对比。
92-
- 可对任意历史录音重新转录,切换不同 ASR 后端并按需叠加 LLM 纠错,方便做同音频对比。
99+
- 可对任意历史录音重新转录,切换不同 ASR 后端并按需叠加 LLM 纠错,方便做同音频对比;也可以把重新处理后的最终文本重放注入到当前应用,验证完整链路
93100
- 批量识别失败时,会在本机历史中保留失败记录和录音,方便后续重新转录,不必整段重说。
94101
- 可配置文本和录音的保留策略(7 / 30 / 180 / 365 天或永久保留)。
95102
- 概览仪表盘:总时长、字符数、AI 纠正次数、平均听写速度——按设备汇总。

README.zh-CN.md

Lines changed: 10 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -19,8 +19,8 @@ VoiceX 是一个跨平台桌面语音输入工具。整体处理链路为:录
1919
- **一键多用** — 单个全局热键驱动三种交互模式:轻点启动免提听写、长按进入按住说话、双击触发翻译。
2020
- **实时 HUD 浮层** — 轻量置顶窗口,实时显示转写文本、录音模式、倒计时和处理状态;在 macOS 多桌面场景下也会跟随当前活跃 Space 显示,不打断当前工作流。
2121
- **LLM 后处理** — 可选将 ASR 输出交给大模型做纠错、翻译或润色,支持自定义 prompt 模板和词典上下文注入。
22-
- **智能文本注入** — 识别结果通过剪贴板粘贴(自动备份/恢复原内容)或模拟键入送入当前应用,无缝衔接
23-
- **历史记录与统计** — 每次听写保留完整元数据(时长、设备、ASR/LLM 模型、原文 vs. 纠正文本),按日期浏览,并支持录音回放与重新转录
22+
- **智能文本注入** — 识别结果通过剪贴板粘贴(自动备份/恢复原内容)或模拟键入送入当前应用,并可按目标应用单独指定注入方式
23+
- **历史记录与统计** — 每次听写保留完整元数据(时长、设备、ASR/LLM 模型、原文 vs. 纠正文本),按日期浏览,并支持录音回放、重新转录和重放注入测试
2424
- **跨设备同步** — 自建同步服务器,在多台设备间保持历史一致。
2525

2626
## 交互模式
@@ -73,6 +73,7 @@ VoiceX 可选将 ASR 输出交给 LLM 做纠错或翻译。支持的提供商:
7373
- **ASR 纠错** — 结合词典上下文和可自定义 prompt 修正识别错误。
7474
- **翻译** — 将听写内容翻译为英文,由双击手势触发。
7575
- **Prompt 模板** — 完全自定义纠错和翻译 prompt,支持 `{{DICTIONARY}}` 占位符注入热词。
76+
- **连通性测试** — 使用当前 provider 和模型发起一次真实纠错请求,检查响应时间和输出质量。
7677

7778
## 词典与热词
7879

@@ -85,11 +86,17 @@ VoiceX 可选将 ASR 输出交给 LLM 做纠错或翻译。支持的提供商:
8586
- **智能标点清理** — 短句自动去除末尾标点(阈值可配置)。
8687
- **关键词替换** — 正则/精确/包含替换规则,在文本注入前执行。
8788

89+
## 文本注入
90+
91+
- 全局支持剪贴板粘贴和模拟键入两种注入方式。
92+
- 可按最近使用的目标应用设置覆盖规则,例如在普通文本框中使用剪贴板粘贴,在对粘贴事件敏感的编辑器中改用模拟键入。
93+
- macOS 上会在热键开始时记录目标应用,降低 HUD 或主窗口抢焦点对注入目标的影响。
94+
8895
## 历史记录与统计
8996

9097
- 全量历史按日期分组,每条记录支持录音回放、复制和详情查看。
9198
- 原始 ASR 输出与 LLM 纠正结果的并排对比。
92-
- 可对任意历史录音重新转录,切换不同 ASR 后端并按需叠加 LLM 纠错,方便做同音频对比。
99+
- 可对任意历史录音重新转录,切换不同 ASR 后端并按需叠加 LLM 纠错,方便做同音频对比;也可以把重新处理后的最终文本重放注入到当前应用,验证完整链路
93100
- 批量识别失败时,会在本机历史中保留失败记录和录音,方便后续重新转录,不必整段重说。
94101
- 可配置文本和录音的保留策略(7 / 30 / 180 / 365 天或永久保留)。
95102
- 概览仪表盘:总时长、字符数、AI 纠正次数、平均听写速度——按设备汇总。

package.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"name": "voicex",
3-
"version": "0.9.5",
3+
"version": "0.10.0",
44
"license": "MIT",
55
"type": "module",
66
"scripts": {

src-tauri/Cargo.lock

Lines changed: 1 addition & 1 deletion
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

src-tauri/Cargo.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
[package]
22
name = "voicex"
3-
version = "0.9.5"
3+
version = "0.10.0"
44
description = "Cross-platform voice input application with ASR"
55
authors = ["VoiceX Contributors"]
66
license = "MIT"

0 commit comments

Comments
 (0)