# A multi-modal GenAI pipeline behind a 24/7 AI radio station
> A global consumer electronics brand wanted a 24/7 radio station where anyone could write a dedication and receive an original song. Twistag built the pipeline behind it: OpenAI writes the lyrics, Suno composes the track and Adobe Firefly creates the cover, each checked for quality before release. Over six months it produced more than 700,000 songs, shared 1.5 million times and seen by 2.4 billion people.

Client: Global consumer electronics brand · Industry: Retail & consumer · Practices: AI & Agents · Timeline: 6 months (June–December 2025)
## Key results
- **700K** original songs generated
- **1.5M** shares
- **2.4B** people reached
- **30M** social engagements
## The challenge

**A song for anyone, at global scale.**

Twistag built the multi-modal generative AI pipeline behind a 24/7 AI radio station for a global consumer electronics brand, producing more than 700,000 original songs that were shared 1.5 million times and seen by 2.4 billion people across a six-month campaign from June to December 2025. Anyone could write a personal dedication and receive a complete song in return — custom lyrics, a full audio track in their chosen genre, and matching album art. Twistag orchestrated three separate AI services behind independent provider abstractions on AWS Lambda, with quality scoring and automatic retry at every stage, so a user never received a failed generation.

The brief was a 24/7 AI-powered song dedication station where anyone could write a personal message and receive a fully original song in return. A real song with custom lyrics, a complete audio track in the user's chosen genre, and album art matching the mood. The brand had the campaign concept and needed a technical platform that could deliver on the emotional promise at global scale. That meant three problems at once. The pipeline: chaining lyrics, audio and image generation into something that feels like one product despite three services, three latency profiles and three failure modes. Scale: a global campaign can multiply concurrent users by twenty in minutes. Quality: a bad output sent to someone's grandmother for her birthday is a PR problem. The client is not named publicly.

## The approach

**Three AI services, one experience.**

1. **Independent stages.** Each AI service sits behind its own abstraction on AWS Lambda, so a provider can be replaced without touching the rest. One was swapped mid-campaign without users noticing. 
2. **Chosen for reliability.** OpenAI for lyrics across six languages, Suno for audio with a dependable quality floor, and Adobe Firefly for artwork with clear commercial licensing for a global brand. 
3. **Quality checked at every stage.** Lyrics are scored for structure and emotional fit, audio for completeness and genre. Anything below threshold is generated again automatically, so no user received a failed song. 

## The impact

**Two shares for every song.**

The campaign ran from June to December 2025. By the end, 700,000 unique songs had been created, shared 1.5 million times, seen by 2.4 billion people, and driving 30 million social engagements worldwide. The number Twistag keeps coming back to is the share-to-creation ratio of roughly two to one: over a million and a half shares against 700,000 creations. Twistag replaced one AI provider mid-campaign without users noticing, because each service sat behind its own abstraction, and the pipeline held through the campaign's traffic spikes without a user ever receiving a failed generation.

> People share AI-generated content when it means something to them.

## Technologies used

- OpenAI
- Suno.AI
- Adobe Firefly
- AWS Lambda

> Twistag built the multi-modal generative AI pipeline behind a 24/7 AI radio station that produced more than 700,000 original songs.

---

Source: https://twistag.com/case-studies/ai-radio-station-multi-modal-genai