Hello everyone, today we are going to introduce a highly acclaimed free AI voice-to-text tool.
memo#
It is the latest product under Feishu, called memo.
It is currently in beta testing, but you can apply for the beta qualification and receive the beta code in one or two days.
The software supports both Windows and Mac clients, and its main function is to convert audio and video into text or subtitles, but it is not limited to that. Let's learn more about it together.
Online Conversion#
Firstly, it supports the conversion of online videos and podcasts, but currently only supports YouTube and a foreign blog platform. After pasting the URL and clicking download, it contains multiple built-in models, which are indicated by star ratings to show the characteristics of different models. You can choose according to your needs. The language refers to the language you want to convert to, whether it is text or subtitles. You can also set some AI prompt words for assistance.
After generating the page, you can choose to export it as subtitles, text, lyrics, markdown, or other formats. If you use Notion as your core working platform, you can also import it automatically. You need to set up your Notion account's API key and page ID in advance.
On this page, you can also edit, translate, and make simple edits to the generated text. Since it is still in beta testing, only video editing is available, and the editing function for audio or podcast content is not yet open.
Now, the first thing that comes to mind is being a content creator. With this tool, you can directly convert foreign videos into Chinese subtitles and publish them on various platforms.
Local Conversion#
The local audio and video conversion function is more versatile. The operation method is the same. But there are more scenarios for use, such as generating English subtitles and text directly from Chinese dubbing. You don't have to wait for the subtitle group to watch the downloaded raw video. It's like combining the online trancy plugin and the local v2sub software.
However, all of this requires you to have your own ChatGPT API key. The advantage is that this software can be used for free, and if you have a low-cost account source, the cost will be lower.
Fig Player#
Tools like Fig Player are AI players themselves, with built-in AI subtitle and translation features.
Subtitle Jun: It uses OpenAI's whisper model for speech recognition, which is equivalent to having a free AI subtitle group. This part uses the whisper model locally, just like memo, so the AI subtitle Jun is completely free.
Translation Jun: It generates translated subtitles based on AI, and you can choose bilingual subtitles. This part runs on the server side and incurs costs, so it is currently free for 2 trials.
You can choose the two software according to your needs. The former is suitable for work, while the latter is for entertainment and watching movies. The former provides a comprehensive service, while the latter only provides video subtitle translation and AI translation.