Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
MiFID II and FCA call recording: compliance for voice transcription in finance
TL;DR: Financial firms operating under MiFID II and FCA jurisdictions must maintain searchable, high-accuracy records of all client-related voice communications, including remote and mobile calls under FCA Market Watch 66. Engineering and product teams building for these obligations typically implement dedicated cloud infrastructure with defined data residency, controls that prevent customer audio from being used to retrain models on Growth and Enterprise plans, and transcription accurate enough that the resulting records hold up under regulatory review. Transcription and speaker attribution errors are not product quality issues in this context. They are audit trail failures, and regulators treat them as such.
Why speech-to-text accuracy matters upstream of your LLM
TL;DR: Downstream LLM performance is ceiling-bounded by upstream transcription accuracy. A transcript with a meaningful error rate doesn't produce proportionally degraded summaries or CRM entries. It produces outputs where hallucinated names, inverted logic, and misattributed speaker turns compound silently into every downstream system that reads them. Prompt engineering cannot recover information the STT layer never captured. Gravite cut call quality review time by 93%, from 15 minutes to 1 minute per call, once transcript accuracy was high enough to trust the output without manual verification.
TL;DR: Telephony audio is constrained to 8kHz narrowband frequencies, stripping away the high-frequency spectral energy that generic 16kHz STT models require. Standard upsampling cannot recover phonemes that were never captured at the source, leading to transcription errors that compound silently into downstream NLU failures. Solaria-3 ranks #1 on Switchboard, the most challenging conversational telephony dataset, ahead of AssemblyAI, ElevenLabs, Deepgram, Mistral, and Speechmatics, ensuring your downstream LLM pipelines receive clean, structured data from real-world noisy call audio.
Gladia and Pipecat partner to push the boundaries of real-time voice AI
Published on May 14, 2025
We’re thrilled to announce a strategic partnership between Gladia and Daily, the team behind Pipecat, aimed at revolutionizing real-time conversational AI. This collaboration combines our cutting-edge audio intelligence capabilities with their flexible 100% open-source framework, empowering developers to create more dynamic, multilingual, and context-aware voice AI applications.
We’re thrilled to announce a strategic partnership between Gladia and Daily, the team behind Pipecat, aimed at revolutionizing real-time conversational AI. This collaboration combines our cutting-edge audio intelligence capabilities with their flexible 100% open-source framework, empowering developers to create more dynamic, multilingual, and context-aware voice AI applications.
Pipecat is a vendor-neutral framework designed to simplify the creation of voice and multimodal conversational agents. It allows developers to orchestrate LLM models and AI services effortlessly, enabling the development of video and voice applications such as personal coaches, meeting assistants, and customer support bots.
Pipecat is maintained by Daily with the support of the global developer community. Daily is a leader in developer tooling and global WebRTC infrastructure since 2016. Earlier this year Daily announced Pipecat Cloud, the first open source voice AI cloud.
About the partnership
At Gladia, we believe the future of human-AI interaction lies in systems that understand and respond in real-time, just like humans do. Pushing the boundaries of ultra low latency conversational AI is key to bridging the gap between humans and machines, enabling more natural, intuitive communication. In today’s world, where seamless interactions are crucial, having AI that can understand diverse languages and contexts is essential for real collaboration in customer support, meetings, and beyond.
This partnership with Pipecat goes beyond technology—it empowers developers to easily create intelligent, adaptable, multilingual voice AI applications that break down barriers and foster meaningful interactions. By combining Gladia's language processing with Pipecat's flexible framework, we can enable the creation of robust voice platforms that meet the needs of a wide range of use cases.
A shared vision for the future
This partnership is more than just a technical integration; it's a shared commitment to pushing the boundaries of what's possible in real-time conversational AI. In the words of Daily's co-founder:
Jean-Louis Queguiner, CEO of Gladia, also shared his excitement for the partnership: "At Gladia, we believe in pushing the boundaries of what's possible in real-time conversational AI. Partnering with Pipecat allows us to extend that vision even further—combining our advanced language processing capabilities with Pipecat’s open-source platform to help developers create truly innovative, scalable voice AI solutions. This collaboration is about more than just technology; it's about shaping the future of human-AI interaction."
What this means for developers
Developers can now leverage the combined strengths of Pipecat and Gladia to build more sophisticated voice AI applications. Whether you're creating a multilingual customer support bot, a real-time meeting assistant, or an interactive storytelling agent, this partnership provides the tools and flexibility needed to bring your vision to life.
To get started, visit pipecat.ai to explore the framework and sign up to the Gladia Playground to try first-hand our newest STT model, Solaria.
Stay tuned for more updates as we continue to innovate and expand the possibilities of real-time conversational AI.
Contact us
Your request has been registered
A problem occurred while submitting the form.
Read more
Speech-To-Text
MiFID II and FCA call recording: compliance for voice transcription in finance
Speech-To-Text
Why speech-to-text accuracy matters upstream of your LLM
.png)
