Frequently Asked Questions
Everything you need to know about Contextli. Can't find your answer? Contact us.
Privacy & Security
Does my audio leave my device?
It depends on which mode you choose:
- Local Whisper:No. Audio is processed entirely on your device. Zero network traffic.
- BYOK Mode:Audio goes directly to your chosen provider (Deepgram, OpenAI, etc.) via their encrypted API. It never touches Contextli servers.
- Cloud Mode:Audio is processed by our secure backend and immediately deleted after transcription.
Do you train AI models on my data?
No. Never. We're a tool company, not a data company. We don't use your recordings, transcripts, or any other content to train models. Your intellectual property remains yours.
Where are my transcripts stored?
All transcripts are stored locally on your computer in the app's data folder. You have full control — view them, export them, or delete them anytime. We never upload or backup your transcripts to our servers.
Is Contextli suitable for sensitive work (legal, medical, NDA)?
Yes. With Local Whisper + Local AI (Ollama), you have a completely air-gapped pipeline. No audio or text ever leaves your machine. Many users in legal and healthcare rely on this for compliance.
Technical
What is "Local AI" and "Ollama"?
Ollama is an open-source tool for running large language models (LLMs) locally on your computer. Contextli integrates with Ollama to enable our "Modes" feature (rewriting transcripts for email, Slack, etc.) without any cloud AI. This means you can use Llama 3, Mistral, or other models completely offline.
What are the hardware requirements?
For Cloud/BYOK modes: Any modern computer works fine. Minimal CPU/RAM usage.
For Local Whisper:
- Mac with Apple Silicon (M1/M2/M3/M4) — Excellent performance
- Windows/Linux with NVIDIA GPU — Very good performance
- CPU-only — Works, but slower on long recordings
For Local AI (Ollama): 8GB+ RAM recommended. 16GB+ for larger models.
Which operating systems are supported?
● macOS — Full support, optimized for Apple Silicon
● Windows 10/11 — Full support including Auto-Paste
● Linux — AppImage/Deb available (community-supported)
How does Auto-Paste work?
When enabled, Contextli automatically pastes the finished transcript into your active application after processing. On macOS, we use AppleScript to simulate Cmd+V. On Windows, we use PowerShell to simulate Ctrl+V. It works with virtually any text field.
Can I use my own API keys?
Yes. BYOK (Bring Your Own Key) mode supports: Deepgram for transcription, and OpenAI, Anthropic, or DeepSeek for AI processing. You pay the providers directly and often save money compared to subscription services.
Pricing & Billing
What's the difference between Lifetime License and Cloud Pro?
Lifetime License ($99 one-time):
- Unlimited local transcription (no per-minute costs)
- Use your own API keys (BYOK) — you pay providers directly
- Local AI via Ollama for complete offline operation
- Lifetime updates included
Cloud Pro ($19/month):
- 10 hours of cloud transcription per month included
- No API keys or setup required — just works
- Access to premium voice models
Is the Lifetime License really lifetime?
Yes. One payment, yours forever. You'll receive all future updates at no additional cost. The only ongoing cost is if you choose to use cloud providers via BYOK (and you pay them directly, not us).
What if I use it fully offline?
With Local Whisper + Local AI (Ollama), there are zero ongoing costs. You paid once for the license, and everything runs on your hardware. No API fees, no per-minute charges, nothing.
Do you offer refunds?
Yes. If Contextli doesn't work for you, contact us within 14 days for a full refund. No questions asked.
Features
What are "Modes"?
Modes are the core feature that makes Contextli different. Instead of raw transcription, Modes transform your speech for specific contexts. Email Mode creates professional emails. Slack Mode creates casual messages. Notes Mode creates bullet points. You can create unlimited custom modes for any use case.
Can I create my own modes?
Absolutely. Custom modes let you define exactly how your speech should be transformed. Examples: "Translate to Spanish", "Write code comments", "Format as meeting notes", "Create LinkedIn post". Each mode can have its own global hotkey for instant access.
What's the floating widget?
A draggable, always-on-top microphone icon that lets you record from anywhere without switching apps. Click to start, see the waveform while recording, and click again to process. It stays out of your way until you need it.
Does it support real-time/streaming transcription?
Yes, via Deepgram's live WebSocket API (requires BYOK or Cloud Pro). You see words appear as you speak — "interim" results in gray, "final" results in black. Great for live captioning or real-time note-taking.