We are excited to announce that Digital Samba's Embedded product now includes a captioning feature, which will enhance the user experience of digital meetings for a lot of our end users.
In the context of digital meetings, captions refer to the text displayed on the screen that transcribes spoken dialogue or other audio content.
Captions can be used to provide accessibility for individuals who are deaf or hard of hearing, as well as to aid comprehension for individuals who speak a different language or who may have difficulty understanding the audio.
As an Integrator, you can enable or disable the captioning feature on a per-room basis via a room setting. You have the option to define a room language, which the AI logic acts on to transcribe the audio into text. We are working on auto-detection of the spoken language, so stay tuned for that to find its way into the platform.
On the dashboard, you can track the usage of this new feature by taking a look at the statistics page where you will find the “captions minutes” metric.
As an end user, you will enjoy the intuitive experience of our implementation as the audio of the speaker is automatically transcribed in real-time. The captions panel is unobtrusively placed by default, but you can change its position on the screen, or hide it entirely.
You have easy access to controls that allow you to change the font size, and if necessary, you can change the language to match the language you speak.
Digital Samba Embedded offers two different operational modes for the AI transcription logic: live-speech and end-of-speech.
The live-speech mode corrects captions on the fly for a more synchronised feel. This mode is well-suited to situations where the speakers communicate clearly in their native language, without heavy accents.
The end-of-speech mode waits until the current speaker finishes their sentence before displaying the transcribed sentence on the screen.The experience is less synchronised, but it’s also less hectic because any corrections made by the AI logic are performed in the background. Integrators should choose the mode that works best for their use case when setting the room preferences.
The Digital Samba Embedded captioning feature can be configured either directly via the platform’s UI or via a programmatic interface. The UI allows the integrator to manipulate various settings directly on the room settings page in the dashboard.
As previously explained, these settings include:
Alternatively, the integrator can use the API to
The SDK methods are not quite ready yet, but we expect to release them very soon. When we do, the integrator will be able to programmatically trigger front-end changes for the local user. You’ll be able to show or hide the captioning feature, define the spoken language and adjust the font of the transcribed text.
We are eager to roll out the new captioning feature to our customers and are convinced it will have a positive impact on the user experience. This is just the first taste of great value-adds coming your way. We are currently working on auto-detection of the spoken language and auto-translation of transcribed text. Further down the line, we will bring you indexed and searchable content in recordings.
If you are looking for a high-quality and easy-to-use digital conferencing solution, Digital Samba Embedded is the perfect choice for you. Your end users will love the seamless implementation of our captioning feature as it brings a new dimension of engagement to their digital meetings.
If you would like to learn more about the captioning feature, please contact one of our representatives. Get ready to take your virtual meetings to the next level!