Get your SDK keys and test for free in the Developer Platform Start now

How BosePark revolutionizes podcast production with ai-coustics

Meet BosePark

BosePark Productions GmbH, located in Berlin, is one of Germany’s leading podcast production companies. They offer end-to-end podcast production solutions, from conception to distribution. Over the past decade, they have produced more than 200 podcast shows for major streaming platforms like Spotify and Audible, as well as prominent organizations such as ARD, ZDF, Wondery, and Der Spiegel. 

BosePark has always been at the forefront of innovation in the audio-visual industry. They were one of the first companies in Europe to offer multilingual podcast production with artificial intelligence. They are always looking out to improve their production workflows to produce the best quality audio.

Portrait of a BosePark Productions CEO, highlighting their innovative approach to podcast production and their partnership with ai|coustics in revolutionizing the industry.

The challenge

“It is a great challenge for us to always guarantee the highest audio quality in the shortest possible production time. We often have very different recording situations, especially when we record guests remotely and cannot control the recording situation there.”
Portrait of a BosePark Productions CEO, Chris Guse highlighting their innovative approach to podcast production and their partnership with ai|coustics in revolutionizing the industry.
Chris Guse
CEO of Bose Park Productions

As a production house known for its fully equipped studio and technical expertise, BosePark ensures top-notch audio quality for all their podcasts and audiobooks produced in-house. However, their biggest challenge often arises from varying recording conditions, particularly with remote guests, which are beyond their control.

These discrepancies lead to issues such as background noise, reverb, and other audio artifacts that detract from the overall quality of the podcasts.

Original audio

ai-coustics WebApp and API

“We found ai-coustics after researching the web and were not only impressed by the simple solution via a web interface but also via the API connection to be able to quickly incorporate the improvement into our production process.”
Chris Guse
CEO of Bose Park Productions

Chris and his team at BosePark recognized the need for a fast and reliable solution to elevate their audio to the highest quality. After thorough research and comparison of various providers, Chris decided to try ai-coustics.

Initially, they started using the ai-coustics WebApp to enhance smaller audio files from older recordings or interviews recorded on mobile phone microphones. They have since upgraded to the ai-coustics API, which allows them to automatically enhance and release audio files with greater efficiency.

Enhanced audio

The outcome and achievement

“ai-coustics effectively mitigates reverb, clipping, and compression artifacts, enabling the team to maintain high audio standards without significant manual intervention. This technology ensures that their podcasts consistently meet professional quality levels.”  

Integrating ai-coustics into BosePark’s workflow has revolutionized their approach to podcast production, ensuring professional-grade audio quality regardless of the recording conditions. Since the partnership, BosePark has received no negative feedback regarding sound quality, a testament to the technology’s impact. The enhanced audio quality has set a new baseline, ensuring all podcasts produced at their studio meet a high standard. This customer success story is just one example of how ai-coustics aims to make production easier and improve content quality in the podcast industry with our generative AI technology.

Latest updates

Voice Focus 1.1 Benchmark Evaluation

This notebook presents a comprehensive evaluation of Voice Focus 1.1 against Krisp BVC and Krisp BVC telephony across two datasets. The analysis includes representative examples and quantitative metrics based on internal development as of February 5, 2025.

Read More
How Synthesia scaled voice cloning quality by improving audio at the source

How Synthesia scaled voice cloning quality by improving audio at the source

As the world’s most widely adopted AI-avatar platform, Synthesia helps teams turn simple text into engaging videos in minutes. Voice cloning sits at the heart of the experience. As the product scaled and adoption grew, it became clear that how voices were captured mattered just as much as how they were generated. Unlike studio voice actors, Synthesia’s users record themselves

Read More
Blog title on dark background with ai-coustics background: What Word Error Rate tells us about Voice AI quality in production

What Word Error Rate tells us about Voice AI quality in production

We talk about Word Error Rate a lot. It’s one of our key metrics in developing and launching new audio enhancement models to improve Voice AI performance. In particular, WER makes a massive difference when it comes to evaluating performance for Speech-to-Text (STT) systems, against a more perceptual quality evaluation like the PESQ and SigMOS methodologies. But what exactly is

Read More

Ready to embrace the power of Voice AI?

Authentic human voices. Studio-quality sound. Real-time capacity. Automated workflows. It starts here.