Using hybrid synthesis when voicing a script using audio recordings allows the robot to reproduce the value of a variable in the same voice that is heard in the original audio file.
Working with hybrid synthesis involves the following steps:
- Creating a variable with the desired value in the script.
- Record an audio file with a voiced phrase, using an example variable value.
- Loading the audio file into the block where the robot should play the value of this variable.
- Marking up the variable in the block settings.
Based on the uploaded audio file, the robot synthesises a voiceover and plays the value of the variable in the given phrase using the same voice. For more information about the process of preparing audio files and setting up hybrid synthesis in scenarios, see Using Hybrid Synthesis.
- The length of the voiced phrase must not exceed 250 characters including the variable value.
- In the source audio file, the sections that are replaced by variable values must not overlap.
- The length of the audio file including the synthesised variable must be at least 3 seconds.
- The normalized text of the variable part should not exceed 25% of the template length. The same restriction applies to the duration of the variable part relative to the final audio file.
- In case you need to voice a larger volume of text or a larger number of variables, split one phrase into several blocks in the script.
- The more exactly the text of the phrase in the script block matches the text of the audio recording, the better the hybrid synthesis will sound.
- When marking up the audio track, a 50 ms indent should be made before and after the synthesised variable.
- It is not recommended to start a phrase with a variable. This may result in the variable sounding incorrectly or not being voiced at all.
- It is recommended to make a recording in good quality and without extraneous noise, as it may affect the quality of synthesis.
- Number of channels: mono (1 channel);
- Compression algorithm: uncompressed (or RSM);
- Sampling rate: 8 kHz;
- Sampling rate: 16 bits;
- Bitrate: 128 kbps;
- File format: .wav;
- File size: 56 KB to 20 MB.