FxFactory’s new Doza Assist Version 1.1.1 now lets you transcribe 25 more languages. You can connect ChatGPT and Claude via MCP and collaborate on your projects by sharing a single link. Transcribing interviews or lots of dialogue into different languages has always been a challenge, but the latest tools, both paid and free, are certainly making it easier.
Doza Assist was designed to help speed up workflows for editors who are working on dialogue-driven footage such as interviews, documentaries, podcasts, panels, keynotes, and event coverage. You can drop in camera files or an existing Final Cut Pro library, and it will transcribe everything on your Mac, as well as label every speaker, and read the full transcript the way a story producer would. It can also find the narrative beats, show the strongest soundbites with timecode and context, and the cutdowns worth pulling for social media distribution.
According to FxFactory, My Style trains on your own portfolio, the scripts, transcripts, and finished pieces that show how you tell a story, so the rough cuts follow your structure and pacing. Without a style loaded, it is claimed to work like a story producer.
Users can ask for the piece in plain language (“build me a 14-minute cut about leaving home”) and a selected sequence lands in Final Cut Pro, Premiere Pro, or DaVinci Resolve with clips, ranges, and markers intact.
According to FxFactory, every part of the pipeline- transcription, speaker identification, and the language model that does the analysis and style matching- runs on-device. Footage stays on your machine, nothing requires an account, and there are no per-minute meters or hour caps.
After the first launch, Doza Assist doesn’t need an internet connection, so you can use it anywhere. If you want frontier-model writing, you can optionally connect your own Anthropic or OpenAI API key.
Pricing & Availability
Doza Assist is a one-off payment of $149 USD.
