Microsoft Speech Platform is free to use TTS provided by Microsoft. It contains many different languages such as English, Spanish, French, Japanese, Korean, Chinese, etc.
The current version is 11. The following is the way of making use of the multilingual TTS. Install the following packages. Runtime: - Runtime Languages: You need to install the “Runtime Languages” package that you are going to use for a certain language (around 50 voices available). The Runtime has 32bit and 64bit version. If it’s not working try install the both. Run the following command in the command prompt (DOS) window as an administrator.
Discover how Speech enables the integration of speech processing capabilities into any app or service. Convert spoken language into text or produce natural sounding speech from text using standard (or customizable) voice fonts. Try any service free—and quickly build speech-enabled apps and services with the following capabilities. Hi Alex, Beginning with Windows Vista and Windows 7, Microsoft Anna is the default and only English voice. It is a SAPI (Speech Application Programming Interface) 5-only voice. However TTS (Text to Speech) engines compatible with SAPI 5 version voices are available from third parties. You can use your favorite search engine to browse for one such.
For 32bit reg COPY “HKEYLOCALMACHINE SOFTWARE Microsoft Speech Server v11.0 Voices Tokens” “HKEYLOCALMACHINE SOFTWARE Microsoft Speech Voices Tokens /s /f - For 64bits reg COPY “HKLM SOFTWARE Wow6432Node Microsoft Speech Server v11.0 Voices Tokens” “HKLM SOFTWARE Wow6432Node Microsoft Speech Voices Tokens” /s /f If it’s not working, try run the both. How to setup in TVML script - Run “regedit” and seek the following “Voice Tokens”. For 32bit: HKEYLOCALMACHINE SOFTWARE Microsoft Speech Voices Tokens For 64bit: HKLM SOFTWARE Wow6432Node Microsoft Speech Voices Tokens - Choose the language package that you are going to use under the Voice Tokens above. “TTSMSfr-FRHortense11″ - Click the ” Attributes” folder then get the value of “Name”. “Microsoft Server Speech Text to Speech Voice(fr-FR, Hortense)” - Extract the voice name from the value above which is in the brackets.
Use the voice name for your TVML script. Syntax is ” character: setvoice(name=A, voicetype=”MSP: voice name“)”. Eg. character: setvoice(name=A, voicetype=”MSP: fr-FR, Hortense “).