Tingo 102.5 FM — Africa's First AI-Powered Radio Station

The Problem and Why It Mattered

I led the end-to-end technical design, infrastructure build, and launch of Tingo 102.5 FM — a live, continuously broadcasting radio station where all content is generated and delivered by AI systems running on GCP. The relevant technical and business risk is the cost of leaving this workflow, control, or product boundary unclear, manual, insecure, or difficult to operate. The case study focuses on the decisions used to make that risk manageable.

Objectives and Success Criteria

• Deliver the capability described in the project objective using a maintainable technical design.
• Make the main workflow, control boundary, and operational responsibilities explicit.
• Produce reviewable implementation evidence without publishing confidential values or customer data.

Requirements and Constraints

The implementation had to be reproducible, observable, and safe to describe publicly without exposing operational secrets or private infrastructure detail.

My Role and Ownership

I owned the technical design and implementation described in this portfolio record, including the technology choices, core system boundaries, and the documentation of the resulting approach. Related organisational decisions, vendor operations, and formal certification decisions remain outside the scope of this technical case study unless stated explicitly.

Solution Overview

The solution is built around Vertex AI, Text-to-Speech API, Cloud Run. Its implementation is organised as the components below so that the architecture, control points, and operating model can be evaluated separately rather than treated as a list of tools.

Architecture and System Design

The public architecture description follows the path from the initiating user, workload, or operator action through the relevant ai engineering components. Access boundaries, data or state handling, and operational controls are described at a safe level; secrets, private addresses, and client-sensitive implementation details are intentionally omitted.

Technology Decisions and Trade-Offs

I selected Vertex AI, Text-to-Speech API, Cloud Run because they support the project objective and make the critical engineering boundaries explicit. The trade-off is operational and platform complexity: the design depends on documented configuration, controlled access, and ongoing review rather than assuming that a managed service or framework removes engineering responsibility.

Implementation Walkthrough

The following implementation notes describe the components that matter most to the project outcome. They are intentionally focused on technical decisions and operating behaviour instead of reproducing entire source files or sensitive configuration.

Implementation: Content Generation Pipeline

News content sourced from RSS feeds and curated APIs, summarised and rewritten for broadcast style using Vertex AI's Gemini models. Programme schedules, station IDs, and DJ transitions generated from configurable templates with time-of-day tone adjustments.

Implementation: Voice Synthesis & Audio Production

GCP Text-to-Speech API (WaveNet and Neural2) synthesises all spoken content. Voice profiles configured for different segments. Audio generated at 44.1kHz/16-bit, mixed with music beds using pydub, mastered to EBU R128 broadcast loudness.

Implementation: Live Stream Infrastructure

Cloud Run service handles listener connections via Icecast protocol. GCP Cloud CDN fronts the stream origin. Tested to 2,000 concurrent connections with automatic scaling configured.

Implementation: Content Operations Dashboard

Next.js + Cloud Run internal dashboard showing the current broadcast queue, real-time listener counts, voice synthesis API cost tracking, and the ability for editors to inject breaking news segments that preempt the scheduled queue.

Implementation: Broadcast Compliance

Vertex AI safety classifiers applied to all AI-generated scripts before voice synthesis — preventing inappropriate content from reaching air. All generated scripts logged to Cloud Storage for regulatory audit.

Implementation: Results

Launched in 2025 as the first fully AI-powered radio station in Africa. 24/7 broadcast with < 0.01% unplanned downtime. Zero human voice talent required for routine programming.

Challenges, Failures and Corrections

This portfolio record does not invent deployment failures, client incidents, or corrective actions that are not supported by the published project evidence. Where operational details are confidential or were not captured for public release, the case study documents the design boundary and lesson instead of presenting an unsupported narrative.

Security, Compliance and Risk

The public record avoids secrets, customer data, and private infrastructure details. The relevant security controls, access boundaries, and operational risks are addressed in the implementation notes where they are material to the project.

Testing, Validation and Evidence

The evidence published for this project is the documented implementation, its stated architecture and controls, and the portfolio record. Launched in 2025 as the first fully AI-powered radio station in Africa. 24/7 broadcast with < 0.01% unplanned downtime. Zero human voice talent required for routine programming. Claims are limited to the implementation details and outcomes documented in this case study.

Results and Evidence

Launched in 2025 as the first fully AI-powered radio station in Africa. 24/7 broadcast with < 0.01% unplanned downtime. Zero human voice talent required for routine programming.

What I Learned

This project reinforced that ai engineering work is not a technology checklist. The durable value comes from making boundaries, trade-offs, ownership, and evidence clear enough for another engineer or stakeholder to review and operate the system responsibly.

What I Would Improve Next

• Expand automated validation around the most important workflow and control boundaries.
• Add or deepen operational evidence, such as dashboards, test artefacts, or an architecture diagram where it is safe to publish one.
• Review the design against the next expected scale, reliability, and governance requirement before extending the system.

Final Takeaway

This cloud engineering case study addresses a defined technical problem through Vertex AI, Text-to-Speech API, Cloud Run. It demonstrates my ability to turn requirements into an explainable design, implement the important controls, and document outcomes and limitations without overstating what the evidence proves.