Designed to be seen
The first AI recorder with a visible recording cue. It turns gently while listening, so everyone in the room knows when capture is on.
Local Context
No required cloud
No extra subscription
OneMira C1
The local context device for builders. Captures Zoom/Teams calls and desk discussions offline for Claude, Codex, and Cursor.
★★★★★7 reviews$89.00 USD
Launch offer: $10 offApplied automatically at checkout.
Key Features:
- Turns real-world discussions into local Context.
- No required OneMira cloud workspace or extra subscription for the core workflow.
- Works with Claude, Codex, Cursor, Claude Desktop, and MCP workflows.
- A rotating turntable makes active capture visible in the room.
Package
Color
Quantity
The highlights
Private by design
Transcription, speaker recognition, and summaries run locally on your computer. No cloud processing. No voice data leaving your device.
No subscription
Capture, transcribe, and organize as much as you want. No monthly fees, no quotas, and no usage meters standing in your way.
Plug into your own AI
Connect instantly with Claude, Codex, Cursor, MCP clients, and your own workflows. One recorder, every AI stack.
Contexts
LLM Wiki
Tasks
Built for agent workflows
Every recording becomes structured knowledge. Automatically organize notes, decisions, and tasks so your AI agents can keep working after the meeting ends.
AI Noise Cancelling
A dedicated AI chip removes background noise in real time and identifies who’s speaking, so every conversation stays easy to follow.
No device hijacking
C1 never takes over your microphone or headphones. Whether you’re on calls or in meetings, it records independently so nothing gets in the way.
30 Hrs
Auto-Record
Always ready
Schedule automatic start/stop windows or trigger it by hand. With up to 30 hours of battery life, C1 is always prepared for your next conversation.
Specifications
- Dimensions
- 60 × 64 × 20 mm
- Weight
- 70 g
- Microphone
- 2 MEMS
- Audio processing
- On-chip neural (RNN) engine + hardware ANC
- Battery
- 1250 mAh
- Operating time
- Up to 30 hrs recording · 60 days standby
- Charging
- USB-C 5V⎓1A · ~2 hrs full charge
- Effective pickup range
- 3 m
- Connection
- Bluetooth 5.4 (LE Audio) · USB-C · No Wi-Fi
- Local processing
- On-device VAD + PC-side local ASR; audio deleted after sync
- Storage
- 32 GB (holds up to 4000 hrs of compressed audio)
- In the box
- OneMira C1 · USB-C cable · User guide
Comparison
Compare with:
OneMira C1
Local plain-text files
Voice Recorder Image Placeholder
Voice recorders
Raw audio recordings
Meeting AI App Image Placeholder
Meeting AI apps
Cloud video call bots
What it hears
In-person talk at your desk
Only what you talk into it
Only your video calls
Who makes sense of it
The AI you already use
You, by re-listening
Their built-in bot
Where it lives
Plain files on your computer
Raw audio on the device
Uploaded to their cloud
To get going
Just talk — it’s already on
Press record every time
Invite a bot to each call
Ongoing cost
No subscription
Often a subscription
Monthly subscription
| Question | OneMira C1 | Voice recorders | Meeting AI apps |
|---|---|---|---|
| What it hears | In-person talk at your desk | Only what you talk into it | Only your video calls |
| Who makes sense of it | The AI you already use | You, by re-listening | Their built-in bot |
| Where it lives | Plain files on your computer | Raw audio on the device | Uploaded to their cloud |
| To get going | Just talk — it’s already on | Press record every time | Invite a bot to each call |
| Ongoing cost | No subscription | Often a subscription | Monthly subscription |
FAQ
1. What is OneMira C1?
A local context device. It captures what is said at your desk, turns it into plain-text notes on your own computer, and makes them available to your own AI over MCP. It is not a cloud note-taker—no transcripts leave your machine. Your AI does the thinking; C1 just hands it the spoken context it never had.
2. How is it different from other cloud AI recorders?
Summaries, recaps, mind maps—every recorder does those. The difference is what happens next. They stop at their own built-in summarizer; C1 hands the conversation to your own agent—Claude, Codex, Cursor—which takes it much further: a real spec, a working doc, a ticket, shipped code. And it is all 100% local, with no subscription and no quota.
3. Where is my data stored? Does anything go to the cloud?
Everything stays on your own computer as plain-text files. Speech recognition, transcription, and speaker labeling all run locally, and the audio is deleted after it syncs. Nothing is uploaded—and because there is no shared cloud, your conversation can never end up on someone else's account.
4. Does it need internet or Wi-Fi?
No. C1 has no Wi-Fi—it connects to your computer over Bluetooth or USB-C, and all processing is offline. The only time the internet is involved is when your own AI tools use it.
5. Which AI tools does OneMira C1 work with? Does it support Chinese dialect transcription?
OneMira C1 works natively with Claude Desktop, Claude Code, Codex, Cursor, and other MCP-compatible or local-file/CLI-based AI tools. Additionally, its local transcription engine supports auto-detection and accurate transcription of English, Mandarin, and major Chinese dialects (like Cantonese and Sichuanese) 100% offline directly on your own machine.
6. How does my agent get to the captured context?
It pulls it from C1 over MCP. Ask your agent in plain language—it finds and calls the right command and works from the context C1 has stored. C1 is the store; your agent does the work.
7. Does C1 edit my AGENTS.md or project files?
No. C1 is a passive store—it never reaches into your repo. Your agent, or a scheduled loop you set up, reads from C1, and you decide what gets written into your AGENTS.md, rules, or docs.
8. Do I need to learn any commands?
No. Just tell your agent what you want in plain language; it discovers and calls the right command on its own. Nothing to memorize.
Customer Reviews
Sign in to Review5.0Based on 7 reviews
57
40
30
20
10
Captures the discussion before it disappears
We built C1 because our best product and architecture decisions were happening at the desk, then getting lost before Claude or Codex could use them. The strongest moment is seeing a messy conversation become local Context an AI can continue from.
Designed for the AI workflow we already use
The useful artifact is not the recording. It is the handoff: decisions, constraints, open questions, and next prompts that can go straight into Claude, Codex, or Cursor without reconstructing the whole conversation from memory.
Built for serious AI workflows
C1 is not trying to be the simplest voice memo app. Pairing the device, running the desktop helper, and initializing local Context is for people who already use AI tools for real work every day.
Local-first changes the feeling of using it
The important promise is control. The core flow should not require sending raw audio into another cloud workspace, and the long-term artifact should be editable local text Context rather than an archive of sensitive recordings.
