Visit our help center if you’re having difficulties or questions about the platform.
While AI is media and production's hottest topic, most standard AI solutions have several flaws and limitations. As it is essential to bring the human in the loop, we preferably talk about ‘Media Intelligence’ instead – a practical approach of blending AI with appropriate human inputs. By closing the learning loop, and taking into account any pre-existing metadata sourced from the production process we succeed in delivering more accurate, more complete, and a far more useful output compared to any alternative on the market
To transcribe audio, index content, subtitling, or enabling content verification, Limecraft integrates a wide range of AI services like Image Recognition and Automatic Speech Recognition (ASR). All carefully trained and configured to deliver the best possible result.
Subject to appropriate configuration, your workspace can be extended to support a variety of image recognition services including face recognition, object detection, animal recognition, or logo detection
Limecraft flawlessly detects different speakers in the audio, which essential for navigating the transcript or creating subtitles.
Limecraft supports a wide range of speech-to-text engines and covers over 200 languages and language flavours. Audio is accurately turned into timed text in seconds.
Besides image recognition aspects like faces and objects, Limecraft also reads text from images.
A number of different Machine Translation services are built in, allowing you to translate transcripts and subtitles for localisation purposes.
The built-in summarisation service uses any pre-existing metadata as well as the result AI transcription and image recognition to generate chapters, each with a summary and a list of keywords
AI services in your workflow are designed to optimise the production process. Right from the start, AI agents operate at the level of an edit assistant. But by continuously refining its training, and integrating more deeply into the production process, it evolves into a powerful collaborator, enabling you to create complex stories that would otherwise be unattainable.
Using a pipeline of AI services, raw material as well as ready to broadcast assets can be automatically ingested, including quality control and content verification.
As a Journalist or Documentary maker, the ability to accurately transcribe interview material in minutes is an essential productivity tool. Use custom dictionaries to ensure correct spelling of brand-specific terminology or proper names.
The combination of speech to text transcription, image recognition, and the summarisation, allows you to identify and select relevant fragments in the blink of an eye
Our signature captioning service turns transcripts into state of the art subtitles, in original and foreign languages, taking into account your styling and timing rules, as well as the the rhythm of the edit.
Alternatively, in case you prefer integrating your own AI services, you can request access to our low-code workflow service. This allows you to access services that have been specifically trained or otherwise trained for performance.
Our extensive REST API opens up the entire media backbone for accessing and modifying by any third-party module. This includes accessing all information about productions, media, metadata and users.
We understand that different customers have different needs in terms of functionality and configuration. Our configurable system allows for adjustments when needed.
