You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Promote Meetings to a first-class feature in README (moved above the
general Features list, dropped the experimental tag, added a release
banner). Bump version 1.6.0-rc2 -> 1.6.0 across package.json,
pyproject.toml, installer/voiceflow.iss, src/lib/constants.ts, and
uv.lock.
Copy file name to clipboardExpand all lines: README.md
+26-20Lines changed: 26 additions & 20 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -21,14 +21,18 @@
21
21
</p>
22
22
23
23
<palign="center">
24
-
<ahref="https://github.com/infiniV/VoiceFlow/releases/tag/v1.6.0-rc1"><imgsrc="https://img.shields.io/badge/Download-Windows-0078D6?style=for-the-badge&logo=windows&logoColor=white"alt="Download for Windows"></a>
25
-
<ahref="https://github.com/infiniV/VoiceFlow/releases/tag/v1.6.0-rc1"><imgsrc="https://img.shields.io/badge/Download-Linux-FCC624?style=for-the-badge&logo=linux&logoColor=black"alt="Download for Linux"></a>
24
+
<ahref="https://github.com/infiniV/VoiceFlow/releases/tag/v1.6.0"><imgsrc="https://img.shields.io/badge/Download-Windows-0078D6?style=for-the-badge&logo=windows&logoColor=white"alt="Download for Windows"></a>
25
+
<ahref="https://github.com/infiniV/VoiceFlow/releases/tag/v1.6.0"><imgsrc="https://img.shields.io/badge/Download-Linux-FCC624?style=for-the-badge&logo=linux&logoColor=black"alt="Download for Linux"></a>
<b>New in v1.6.0 — <ahref="#meetings">Meetings</a>:</b> long-form recording with mic + system audio, local transcription, and bring-your-own-LLM summaries.
32
36
</p>
33
37
34
38
---
@@ -39,6 +43,24 @@ VoiceFlow lives in your system tray. Hold a global hotkey, a small popup pops up
39
43
40
44
The inference runs on your machine through [faster-whisper](https://github.com/SYSTRAN/faster-whisper). CUDA when you have it, CPU when you don't. The audio never touches a network socket.
41
45
46
+
<h2id="meetings">Meetings <sub><sup>new in v1.6.0</sup></sub></h2>
47
+
48
+
Long-form recording that captures your mic plus system audio (Zoom, Meet, anything that plays through your speakers) into one stereo file, transcribes it locally with Whisper, and runs the summary through an LLM provider you choose.
49
+
50
+
<palign="center">
51
+
<imgsrc="media/meetings-detail.png"alt="Meeting detail with transcript, summary, and audio player"width="100%">
52
+
</p>
53
+
54
+
-**System audio + mic in one file.** Stereo capture via WASAPI loopback (Windows) and PipeWire/PulseAudio (Linux).
55
+
-**Pause, resume, stop** from the dashboard or the tray menu — recording survives across hour-long calls.
56
+
-**Re-transcribe** any saved recording with a different model, device, or language without re-recording.
57
+
-**Bring your own LLM.** OpenAI, Groq, OpenRouter, Ollama, or any OpenAI-compatible endpoint. Keys live in your OS keychain.
58
+
-**Auto-rename** from a default timestamp to a real topic once the transcript lands.
59
+
-**Export** to Markdown, plain text, SRT, or structured JSON.
60
+
-**Built-in playback** via the `voiceflow://` URL scheme — jump straight from any transcript line into the audio.
61
+
62
+
Recording, transcription, search, and storage stay local. The only network call is the optional summary request — skip it, point it at a local Ollama, or send it to a provider you already pay for.
63
+
42
64
## Features
43
65
44
66
-**Fully local.** Audio stays in RAM. No telemetry, no analytics, no phone-home.
@@ -50,22 +72,6 @@ The inference runs on your machine through [faster-whisper](https://github.com/S
50
72
-**Searchable history.** SQLite log of every transcript, stored at `~/.VoiceFlow/`.
51
73
-**Dark mode by default.** Light and system themes if you want them.
52
74
53
-
## Meetings (experimental)
54
-
55
-
New in [`v1.6.0-rc1`](https://github.com/infiniV/VoiceFlow/releases/tag/v1.6.0-rc1). Long-form recording that captures mic input plus system audio (Zoom, Meet, anything that plays through your speakers) into one stereo file, transcribes it locally, and lets you bring your own LLM for the summary.
56
-
57
-
<palign="center">
58
-
<imgsrc="media/meetings-detail.png"alt="Meeting detail with transcript, summary, and audio player"width="100%">
59
-
</p>
60
-
61
-
- Pause, resume, and stop from the dashboard or the tray menu.
62
-
- Re-transcribe any saved recording with a different model, device, or language without re-recording.
63
-
- Bring your own LLM provider: OpenAI, Groq, OpenRouter, Ollama, or any OpenAI-compatible endpoint. API keys are stored in your OS keychain.
64
-
- Export to Markdown, plain text, SRT, or structured JSON.
65
-
- Auto-rename from a default timestamp to a real topic once the transcript is in.
66
-
67
-
Recording, transcription, search, and storage stay local. The only network call is the optional summary request, and you can skip it, point it at a local Ollama, or send it to a provider you already pay for.
68
-
69
75
## VoiceFlow vs cloud dictation
70
76
71
77
|| VoiceFlow | Cloud services |
@@ -78,7 +84,7 @@ Recording, transcription, search, and storage stay local. The only network call
78
84
79
85
## Install
80
86
81
-
Grab the latest binary from [Releases](https://github.com/infiniV/VoiceFlow/releases) — currently [`v1.6.0-rc1`](https://github.com/infiniV/VoiceFlow/releases/tag/v1.6.0-rc1) (pre-release):
87
+
Grab the latest binary from [Releases](https://github.com/infiniV/VoiceFlow/releases) — currently [`v1.6.0`](https://github.com/infiniV/VoiceFlow/releases/tag/v1.6.0):
0 commit comments