Open Menu
Lyrebird

Generative AI for next-generation multimedia

Lyrebird is Fluendo’s Generative AI research initiative, combining deep in-house multimedia engineering expertise with sovereign, controllable model architectures across audio, speech, and video, in full compliance with GDPR and the EU AI Act.

Talk to an expert!
Grid
Code

Generative AI is reshaping multimedia

Lyrebird explores how generative intelligence can power next-generation multimedia solutions enabling intelligent media generation, transformation, and enhancement from the edge to the cloud, integrating generative models directly into deterministic media pipelines.

The Lyrebird initiative represents Fluendo’s strategic framework to bridge cutting-edge generative AI with over two decades of open-source multimedia expertise.

overview_01
Research line description

Key strategic pillars

Lyrebird investigates end-to-end generative AI systems designed for real-world multimedia ecosystems. Our research focuses on the following core strategic pillars:

  • Any-to-any multimodal generation: Investigating cross-modal architectures (speech-to-speech, text-to-speech/audio, video generation, and multimodal synthesis) that integrate into low-latency streaming and processing pipelines.
  • European sovereignty & data governance: Developing transparent, sovereign AI models with verifiable training provenance, strict data residency, and full alignment with European regulatory frameworks (GDPR, EU AI Act). Models are architected so that proprietary user data remains confidential and is never ingested for unauthorized retraining.
text

our use cases

Concepts with real-world potential

These use cases present conceptual examples of how our ideas and technologies could address real-world industry challenges.

overview

Catalan Text-to-Speech Software

The Catalan audiovisual sector currently faces a significant technological gap regarding high-quality, professional-grade synthetic voice solutions. Foundation Text-to-Speech (TTS) technologies work effectively for the majority of languages with large numbers of speakers, such as English, Chinese, and Spanish. Nevertheless, for regional languages like Catalan, these models do not deliver adequate performance and fail to meet the needs of the phonetic nuances and dialectal diversity required for professional dubbing and media production. Furthermore, the rise of generative AI has raised urgent concerns about the privacy of biometric data and the intellectual property rights of voice actors.

Due to these challenges, the industry would require a secure, sovereign, and ethically grounded platform to generate high-fidelity Catalan synthetic speech. It would be essential to establish a system that not only achieves naturalness through advanced Computer Vision and MLOps principles but also ensures total compliance with the EU AI Act and GDPR.

Catalan serves as a proof of concept for sovereign technology in other underrepresented European regional languages.

Bits & Bytes

Explore our blog, one byte at a time. Our team unpack our latest news, industry insights and in-depth articles to connect you with the multimedia world.

Blog

Read more about our work

View All
IA-Veu building legal, ethical, and trustworthy AI voice technology in Catalan

IA-Veu building legal, ethical, and trustworthy AI voice technology in Catalan

broadcasting, multimedia-edge-ai, lyrebird

IA·Veu is a professional AI voice technology in Catalan, designed for the audiovisual industry with a strong focus on legality, ethics, and content traceability.

Read more