TTS - Text to Speech
On this page |
|
Overview
This section contains the blocks that can be used for text-to-speech conversion.
You can select your preferred provider from the list of those integrated with XCALLY, that you can find in the next paragraphs.
Important
Please note that TTS providers are third-party applications. Their functionalities, costs, and behaviors depend on the specific provider you choose.
Requirements for TTS blocks to function properly:
A stable internet connection.
A valid account with the selected TTS provider.
Google Cloud TTS
The Google Cloud TTS block allows to perform Text-to-Speech conversion using Google Cloud TTS.
Fields
Label: enter a short description for the block
Provider: select the Google Cloud Provider account from the dropdown list
Text Type: select Text (PlainText) or SSML (Speech Synthesis Markup Language: refer to Google official documentation to find out more about how to use it)
Text: enter the text you would like to convert to speech using TTS
Language Code: the language you would like to use
Voice Type: select one of the proposed types like News, Standard, Studio, Polyglot
Voice Name: select the voice of the operator, choose between Female/Male and voice type
Speaker Type: select the device profile like smartphones, headphones, car speakers.
Speed: define the speed at which the TTS engine reads the text
Pitch: adjust the intonation of the generated voice
Exit Arrows
The Google Cloud TTS block provides just one arrow out to the next step
Google TTS
The Google TTS block allows to perform Text-to-Speech conversion using Google TTS, for internal testing.
Fields
Label: enter a short description for the block
Text: enter the text you would like to convert to speech using TTS. The maximum text length allowed is 200 characters.
Language: select the language you would like to use from the dropdown list
Exit Arrows
The Google TTS block provides just one arrow out to the next step
We do not recommend using this block in a production environment, as it is intended for testing purposes only.
For production, we recommend using Google Cloud TTS.
iSpeech TTS
The iSpeech block allows to perform Text-to-Speech conversion using the iSpeech TTS Agi Parameters
Fields
Label: enter a short description for the block
Text: enter the text you would like to convert to speech using TTS
Key: insert your license key from the ispeech.org account
Language: the language you would like to use for the translation, select it from the dropdown list
Speed: define the speed at which the TTS engine reads the text
Interrupt key: set a a key or digit that, when pressed by the user, can interrupt the ongoing speech playback.
Exit Arrows
The iSpeech block provides just one arrow out to the next step.
AWS Polly
The AWS Polly block allows to perform Text-to-Speech conversion using AWS Polly Agi Parameters.
Fields
Label: enter a short description for the block
Access Key ID and Secret Access Key: insert AWS security credentials. See AWS Polly documentation
Region: select the AWS regional endpoint. See AWS Polly documentation
Voice: select the voice used for the synthesis, from the dropdown list
Text: enter the text you would like to convert to speech using TTS
Text Type: specifies whether the input text is plain text or SSML. The default value is plain text. See AWS Polly documentation
Exit Arrows
The AWS Polly block provides just one arrow out to the next step
OpenAI TTS
FROM VERSION 3.49.0
The OpenAI TTS block allows to perform Text-to-Speech conversion using OpenAI TTS.
Fields
Label: enter a short description for the block
OpenAI Cloud Provider previously configured that you want to use
Model of TTS to use between TTS-1 and TTS-1 High Definition
Voice Name: select the voice of the operator that will speak the output
Text: enter the text you would like to convert to speech using TTS
To discover more about text to speech with OpenAI, you can explore official documentation
Please note the OpenAI output is MP3.
Exit Arrows
The OpenAI TTS block provides just one arrow out to the next step
Lumenvox TTS
Important: you must install Lumenvox on a machine that is reachable by your system.
The Lumenvox TTS block allows to perform Text-to-Speech conversion using Lumenvox TTS
Fields
Label: enter a short description for the block
Text: enter the text you would like to convert to speech using TTS
Options: here you can define details about the synthesis. Valid options are:
l - language to use (e.g. "en-GB", "en-US", "en-AU", etc.)
v - voice name to use (e.g. "Lindsey", "Chris", etc.)
g - voice gender to use (e.g. "male", "female")
p - profile to use, as specified in the mrcp.conf file
i - digits to allow the TTS to be interrupted with (can specify "any" to allow any digits to interrupt)
f - filename on disk to store audio to (audio not stored if not specified or empty)
epe – exit on a play error
pv - prosody volume (silent/x-soft/soft/medium/load/x-loud/default)
pr - prosody rate (x-slow/slow/medium/fast/x-fast/default)
Multiple options can be provided by joining options with an ampersand, e.g. l=en-US&g=female
Exit Arrows
The Lumenvox TTS block provides just one arrow out to the next step
Sestek TTS
The Sestek TTS block allows to perform Text-to-Speech conversion using Sestek TTS.
Fields
Label: enter a short description for the block
Text: enter the text you would like to convert to speech using TTS
Options: they control details about the synthesis. Valid options are:
l - language to use (e.g. "en-GB", "en-US", "en-AU", etc.)
v - voice name to use (e.g. "Lindsey", "Chris", etc.)
g - voice gender to use (e.g. "male", "female")
p - profile to use, as specified in the mrcp.conf file
i - digits to allow the TTS to be interrupted with (can specify "any" to allow any digits to interrupt)
f - filename on disk to store audio to (audio not stored if not specified or empty)
epe – exit on a play error
pv - prosody volume (silent/x-soft/soft/medium/load/x-loud/default)
pr - prosody rate (x-slow/slow/medium/fast/x-fast/default)
Multiple options can be provided by joining options with an ampersand, e.g. l=en-US&g=female
Exit Arrows
The Sestek TTS block provides just one arrow out to the next step
UniMRCP Synth
To make this block work you must install MRCP Synth on a machine that is reachable by your system.
The UniMRCP Synth block lets you perform a Text-To-Speech conversion based on MRCP.
Fields
Label: enter a short description for the block
Text: enter the text you would like to convert to speech using TTS
Options: they control details about the synthesis. Valid options are:
l - language to use (e.g. "en-GB", "en-US", "en-AU", etc.)
v - voice name to use (e.g. "Lindsey", "Chris", etc.)
g - voice gender to use (e.g. "male", "female")
p - profile to use, as specified in the mrcp.conf file
i - digits to allow the TTS to be interrupted with (can specify "any" to allow any digits to interrupt)
f - filename on disk to store audio to (audio not stored if not specified or empty)
epe – exit on a play error
pv - prosody volume (silent/x-soft/soft/medium/load/x-loud/default)
pr - prosody rate (x-slow/slow/medium/fast/x-fast/default)
Multiple options can be provided by joining options with an ampersand, e.g. l=en-US&g=female
Exit Arrows
The MRCP TTS block provides just one arrow out to the next step