diff --git a/README.md b/README.md index 7f45e4d..29ce1b4 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,8 @@ just the Python standard library and PyQt6. | | | |---|---| | API and models | Cleanup rules | -| Audio file | History | +| Agent | Meeting | +| Audio file | Shortcuts | ## Install @@ -42,16 +43,14 @@ puts all of that back, keeping the keys you chose; `./uninstall.sh` takes it awa again and leaves your settings and dictations alone unless you pass `--purge`. Speech to text and cleanup each pick a provider in the settings window, and both -can run here, on whisper.cpp and llama.cpp: the program and the model are -downloaded from that window, checksummed, so nothing has to be installed first -and nothing leaves the machine. Otherwise speech to text runs on **OpenAI**, -**Groq** or **OpenRouter** (`gpt-4o-transcribe` by default) and cleanup on -OpenRouter (`google/gemini-3.5-flash-lite`) or, when either is installed, on -Claude Code or Codex. The keys fall back to `OPENAI_API_KEY`, `GROQ_API_KEY` and -`OPENROUTER_API_KEY`, and are -stored in `~/.config/dikte/config.json`, mode 600. Cleanup can be switched off, -in which case the raw transcript is pasted, and a thinking model's effort can be -set next to it. +run here by default, on models of your own. The cloud is the other option: +speech to text on **OpenAI**, **Groq** or **OpenRouter** (`gpt-4o-transcribe`), +cleanup on OpenRouter (`google/gemini-3.5-flash-lite`) or, when either is +installed, on Claude Code or Codex. The keys fall back to `OPENAI_API_KEY`, +`GROQ_API_KEY` and `OPENROUTER_API_KEY`, and are stored in +`~/.config/dikte/config.json`, mode 600. Cleanup can be switched off, in which +case the raw transcript is pasted, and a thinking model's effort can be set next +to it. ## Using it @@ -81,6 +80,12 @@ running. ## What it does +- **It all runs on this machine by default.** Speech to text on whisper.cpp and + cleanup on llama.cpp, neither installed beforehand: the settings window fetches + the program and the model, verifies the sha256 and refuses a download published + without one, then keeps a server alive while you dictate. The graphics card is + reached through CUDA, ROCm or Vulkan where the build allows. No key, no + account, nothing leaving the machine. - **Silence never reaches the API.** Handed near-silence, a transcription model invents a sentence instead of returning nothing ("Thanks for watching", or in Turkish "Altyazı M.K."). A recording is dropped when nothing rose 10 dB above diff --git a/README.tr.md b/README.tr.md index f60087b..38c4639 100644 --- a/README.tr.md +++ b/README.tr.md @@ -16,7 +16,8 @@ sadece Python standart kütüphanesi ve PyQt6. | | | |---|---| | API ve modeller | Temizleme kuralları | -| Ses dosyası | Geçmiş | +| Ajan | Toplantı | +| Ses dosyası | Kısayollar | ## Kurulum @@ -42,11 +43,9 @@ son sürümü çeker ve bunları senin seçtiğin tuşlarla yerine koyar; diktelerine dokunmaz. Sesi yazıya çevirme ve temizleme, ayarlar penceresinde ayrı ayrı sağlayıcı -seçer; ikisi de burada çalışabilir, whisper.cpp ve llama.cpp üzerinde: program da -model de o pencereden, sha256 doğrulamasıyla indirilir, yani önceden hiçbir şey -kurman gerekmez ve makineden hiçbir şey çıkmaz. Bulutu seçersen sesi yazıya -çevirme **OpenAI**, **Groq** ya da **OpenRouter**'da (varsayılan -`gpt-4o-transcribe`), temizleme OpenRouter'da +seçer; ikisi de varsayılan olarak burada, kendi modellerinle çalışır. Bulutu +seçersen sesi yazıya çevirme **OpenAI**, **Groq** ya da **OpenRouter**'da +(varsayılan `gpt-4o-transcribe`), temizleme OpenRouter'da (`google/gemini-3.5-flash-lite`) ya da kuruluysa Claude Code veya Codex'te çalışır. Anahtarları boş bırakırsan `OPENAI_API_KEY`, `GROQ_API_KEY` ve `OPENROUTER_API_KEY` kullanılır; anahtarlar `~/.config/dikte/config.json` @@ -81,6 +80,12 @@ olmasını ister. ## Neler yapıyor +- **Her şey varsayılan olarak bu makinede çalışır.** Sesi yazıya çevirme + whisper.cpp, temizleme llama.cpp üzerinde; ikisini de önceden kurman gerekmez: + ayarlar penceresi programı ve modeli indirir, sha256'sını doğrular, + checksum'suz yayınlanmış bir indirmeyi reddeder, sen dikte ettikçe sunucuyu + ayakta tutar. Derleme destekliyorsa ekran kartına CUDA, ROCm ya da Vulkan + üzerinden ulaşılır. Anahtar yok, hesap yok, makineden çıkan bir şey yok. - **Sessizlik API'ye gitmez.** Sessize yakın bir ses verildiğinde model boş dize döndürmez, bir cümle uydurur ("Altyazı M.K.", "Thanks for watching"). *O kaydın kendi* gürültü tabanının 10 dB üstüne en az 0,3 saniye çıkan bir şey diff --git a/docs/settings-agent.webp b/docs/settings-agent.webp new file mode 100644 index 0000000..d693658 Binary files /dev/null and b/docs/settings-agent.webp differ diff --git a/docs/settings-api.webp b/docs/settings-api.webp index afcf3e0..142a435 100644 Binary files a/docs/settings-api.webp and b/docs/settings-api.webp differ diff --git a/docs/settings-audio-file.webp b/docs/settings-audio-file.webp index 3b113f9..f5d77f0 100644 Binary files a/docs/settings-audio-file.webp and b/docs/settings-audio-file.webp differ diff --git a/docs/settings-cleanup.webp b/docs/settings-cleanup.webp index ff87c00..725b0b0 100644 Binary files a/docs/settings-cleanup.webp and b/docs/settings-cleanup.webp differ diff --git a/docs/settings-general.webp b/docs/settings-general.webp index 498ee8e..18bcef7 100644 Binary files a/docs/settings-general.webp and b/docs/settings-general.webp differ diff --git a/docs/settings-history.webp b/docs/settings-history.webp deleted file mode 100644 index 3f108df..0000000 Binary files a/docs/settings-history.webp and /dev/null differ diff --git a/docs/settings-meeting.webp b/docs/settings-meeting.webp new file mode 100644 index 0000000..13b59e4 Binary files /dev/null and b/docs/settings-meeting.webp differ diff --git a/docs/settings-shortcuts.webp b/docs/settings-shortcuts.webp new file mode 100644 index 0000000..73ba99a Binary files /dev/null and b/docs/settings-shortcuts.webp differ