Generate speech
(Created page with "'''generate speech''' is a command that generates speech from the given text, using the specified voice. The Refresh parameter forces the speech to be regenerated, providing...") |
|||
| Line 1: | Line 1: | ||
'''generate speech''' is a command that generates speech from the given text, using the specified voice. | '''generate speech''' is a command that generates speech from the given text, using the specified voice. | ||
| − | The | + | The Speech Synthesis commands use the Eleven Labs API to generate highly realistic sounding speech. Since there is some lag time in creating the audio, UBot Studio saves the all the audio generated to the hard drive. This way, when you play the speech audio, it can be played immediately instead of needing to wait for it to generate. |
| + | |||
| + | the '''generate speech''' command allows you to generate the speech audio and save it to the hard drive, so that it will play in real time if you later use '''start playing speech'''. This is not required, but can be convenient for applications that require real time playback. | ||
== Parameters == | == Parameters == | ||
| Line 7: | Line 9: | ||
'''Text:''' The text that you want to convert into speech. | '''Text:''' The text that you want to convert into speech. | ||
| − | '''Voice:''' The voice that you want to use for the speech synthesis. | + | '''Voice:''' The voice that you want to use for the speech synthesis. The values in the dropdown are provided by default by Eleven Labs. If you have created or imported other voices, you can manually enter the name of any voice in your account. |
| − | '''Refresh:''' | + | '''Refresh:''' If set to True, this command will regenerate the audio even if it was previously generated. If set to false, the command will only generate new audio if the audio for the text was not previously generated. It defaults to False. |
== Example == | == Example == | ||
| Line 15: | Line 17: | ||
<pre> | <pre> | ||
connect to speech synthesis("your API key") | connect to speech synthesis("your API key") | ||
| − | generate speech("Hello, UBot Studio!", " | + | generate speech("Hello, UBot Studio!", "Rachel", True) |
| + | start playing speech("Hello, UBot Studio!", "Rachel", False) | ||
| + | wait for speech | ||
</pre> | </pre> | ||
| − | Please replace "your API key" with your actual API key for | + | Please replace "your API key" with your actual API key for Eleven Labs. |
| − | In the script provided, "Hello, UBot Studio!" is converted into speech using the " | + | In the script provided, "Hello, UBot Studio!" is converted into speech using the "Rachel" voice. The 'refresh' parameter is set to true, meaning that if the speech was previously generated, it will be regenerated. |
| − | + | The script then plays the generated audio, and waits for it to finish. | |
Latest revision as of 17:15, 12 July 2023
generate speech is a command that generates speech from the given text, using the specified voice.
The Speech Synthesis commands use the Eleven Labs API to generate highly realistic sounding speech. Since there is some lag time in creating the audio, UBot Studio saves the all the audio generated to the hard drive. This way, when you play the speech audio, it can be played immediately instead of needing to wait for it to generate.
the generate speech command allows you to generate the speech audio and save it to the hard drive, so that it will play in real time if you later use start playing speech. This is not required, but can be convenient for applications that require real time playback.
[edit] Parameters
Text: The text that you want to convert into speech.
Voice: The voice that you want to use for the speech synthesis. The values in the dropdown are provided by default by Eleven Labs. If you have created or imported other voices, you can manually enter the name of any voice in your account.
Refresh: If set to True, this command will regenerate the audio even if it was previously generated. If set to false, the command will only generate new audio if the audio for the text was not previously generated. It defaults to False.
[edit] Example
connect to speech synthesis("your API key")
generate speech("Hello, UBot Studio!", "Rachel", True)
start playing speech("Hello, UBot Studio!", "Rachel", False)
wait for speech
Please replace "your API key" with your actual API key for Eleven Labs.
In the script provided, "Hello, UBot Studio!" is converted into speech using the "Rachel" voice. The 'refresh' parameter is set to true, meaning that if the speech was previously generated, it will be regenerated.
The script then plays the generated audio, and waits for it to finish.
