Speech to Text transcription for Video Recordings
Budget: €30 – €250 EUR
We have to analyze the video recordings of our sellers. There are one or more speakers in each video recording.
Currently we support German & English.
We need a software built as a service which converts speech to a text transcript with individual speaker separated. We need also the time to be recorded.
In the Web Application, we will display the video & also the transcript. When the user will click on a specific transcripted line, it should automatically move the cursor in the video to that minute:second. The same should also be possible viceversa.
When the user will be watching the video, we would like to keep the cursor at the right position in transcript text.
For this purpose,
1. We need speech to text transcription separated by each speaker and time.
2. The transcript must be accurate. Supported Languages: German & English. Note that a video recording may have both languages included. Software has to identify it automatically
The project shall be considered failed if the above 2 criteria's are not met.
Suggest the suitable software + approach to achieve the same. The output shall be in JSON format.
There are many open source & paid solutions available in the market. Please do not use any open source which prohibits commercial usage.
Currently we support German & English.
We need a software built as a service which converts speech to a text transcript with individual speaker separated. We need also the time to be recorded.
In the Web Application, we will display the video & also the transcript. When the user will click on a specific transcripted line, it should automatically move the cursor in the video to that minute:second. The same should also be possible viceversa.
When the user will be watching the video, we would like to keep the cursor at the right position in transcript text.
For this purpose,
1. We need speech to text transcription separated by each speaker and time.
2. The transcript must be accurate. Supported Languages: German & English. Note that a video recording may have both languages included. Software has to identify it automatically
The project shall be considered failed if the above 2 criteria's are not met.
Suggest the suitable software + approach to achieve the same. The output shall be in JSON format.
There are many open source & paid solutions available in the market. Please do not use any open source which prohibits commercial usage.