Speech in.
Text out, live.
Voice-Transcribe transcribes calls, meetings, and voice notes live with speaker detection — as a standalone tool or built directly into the Cold-Call add-on. Launching soon as a separately priced add-on — pricing will be announced in good time.
What's included
Live transcription
Microphone alone, or microphone + system audio (e.g. for video calls) — the text keeps pace as people speak.
Speaker detection
Multiple speakers are automatically distinguished and shown in separate colors.
Many languages
Automatic language detection or a fixed selection — from German and English to over 20 other languages.
Usable directly in Cold-Call
While calling in the Cold-Call add-on, the same transcript runs live and automatically attaches to the call.
Export & copy
Export as .txt or .json, or copy the entire transcript to the clipboard with one click.
Your own API key per login
Every team member brings their own AssemblyAI account — the free starting credit covers around 185 hours.
How it works
Add your API key
Create a free AssemblyAI account, enter the key in settings.
Start recording
Meeting, call, or voice note — one click is all it takes, and the transcript runs live.
Edit & export
Adjust speaker names, copy, or export as a file.
Frequently Asked Questions
Launching soon
Voice-Transcribe is a separately priced add-on launching soon — pricing will be announced in good time. Reach out informally to join the waitlist.
Your own data storage, kept separate from other vendors — your team shares a common base.