Site icon techcoffeehouse.com

Toku Launches Visual Builder for Speech AI in Singapore

A textured flat illustration in a warm, cozy editorial style. A simple microphone sits at the start of a gently curving line of connected building blocks, each one glowing softly, flowing toward a small outline of Singapore's skyline in the background. Style: Simplified, stylized forms with minimal detail. Soft organic grain texture. Muted autumnal color palette (warm yellows, oranges, browns, sage greens, cream backgrounds). Single soft light source creating subtle shadows. Flat shapes with no 3D rendering. Thin consistent outlines. Mid-century modern illustration influence. Composition: Clear focal point, balanced layout, environmental details rendered simply. Generous negative space. 16:9 landscape. Mood: Calm, warm, relatable, editorial, lifestyle. Technical: High resolution, matte finish, no harsh gradients. No text, no logos, no recognisable faces.
Advertisements

Toku Ltd, the Singapore-headquartered AI-powered customer experience platform, has launched Makimoto Flows, a visual builder that lets developers assemble, test and customise speech AI pipelines on a single canvas – with every processing step kept within Singapore.

Makimoto Flows builds on Toku’s open-source Makimoto initiative, launched in April, extending its capabilities beyond transcription to let developers combine transcription, summarisation and call tagging into customisable pipelines. The tool adds a visual layer on top of Toku’s Kawa transcription API and its summarisation and tagging endpoints.

Building and testing speech AI pipelines visually

Developers using Makimoto Flows can connect transcription, summarisation and call-tagging blocks, test each step on a recorded call, and compare results whenever a block is adjusted and rerun. The tool is designed to help teams move from experimentation to development: starting from a Chained Analysis template, developers can adjust any block and export their pipeline as ready-to-run Python code for integration into their own applications, including call recaps and call triage.

Keeping speech data in Singapore

A central feature of the launch is data residency. Every step of a Makimoto Flows pipeline – audio recordings, transcripts and the resulting analysis – is processed and kept in-country, giving developers greater control over where their data is handled. The emphasis reflects growing demand among regional enterprises for AI infrastructure that keeps sensitive voice data within national borders.

“Models will keep changing. The ability to compose them, and to know where they run, is what lasts,” said Thomas Laboulle, Toku’s founder and CEO.

Makimoto Flows is now live at makimoto.ai, where developers can create a free account and test speech AI pipelines with 1,000 free minutes included. Toku said that as speech AI moves beyond transcription into more complex applications, developers need greater control over how it works – from the models they use to how each stage connects and where it runs.

Author

Exit mobile version