We just shipped Makimoto Flows, a visual builder for speech AI pipelines. Drag Transcribe, Summarise and Tags blocks onto a canvas, run them on audio or text, and inspect each step's output. When it works, export the pipeline as JSON, cURL or Python SDK code. Kawa, the orchestration layer underneath, is open source on GitHub.

Try it now for free->

TL;DR:
• Three templates plus a blank canvas
• Call tagging across seven categories, including customer sentiment and malicious agent behaviour
• 1,000 free transcription minutes on every account

Read the full release article->

What block should we build next?

Explore the documentation:

• Sign Up for a Free Account

• Visit Makimoto
• Join the Makimoto Discord community
• View Kawa on GitHub
• View the Makimoto Python SDK