Voice Reader Server 22

The flexible solution for the integration of top-quality text-to-speech in your company

Voice Reader Server 22 Text to Speech offers everything you need to automatically convert all texts into high-quality voice recordings. Whether you want to announce current reports such as traffic updates, integrate voice output in your call center, sound-track eLearning applications, make public transport announcements or provide large volumes of text in audio format also – Voice Reader Server 22 TTS is the ideal solution to supplement any application or workflow with high-quality voice output.

The benefits at a glance:

• Fast and efficient conversion of text to audio
• Dynamic changing between male and female voices
• Customized voices through control of pitch, speaking speed, timbre and volume
• Simple pronunciation correction through user dictionaries
• High data throughput for fast response times
• Resource efficiency thanks to intermediate storage of audio files
• Simple integration into many applications and workflows

The most important plus points of our text-to-speech solution Voice Reader Server 22

• Dynamic changing between different voices
  Change between male and female voices.
  Individual customizability of speed, pitch, timbre and volume in the text.
  Change of language (if several languages are used).
• Flexible control of the audio format and tone quality
  Depending on the application (e.g. telephone, computer, radio or recorded messages on phones) you can control which audio format requires which tone quality:
  WAV format: 8 /11 /22 /44 /48 kHz; 8 Bit Mono and 16 Bit Mono
  MP3 format: 16 to 160 kbps
• Easy pronunciation changes
  With the Voice Reader Studio 22 version included in the delivery scope, the pronunciation can be individually adjusted, e.g. for proper names or foreign-language expressions.
• Fast installation and handling
  The documentation and code samples included in the delivery facilitate simple installation and trouble-free use of Voice Reader Server 22 text-to-speech in your company.
• Simple integration into all workflows
  Via the HTTP interface, the voice output can be integrated into any application and workflow. The interface can be called up with all the standard programming languages. In the post request, you can decide whether pure text, HTML or XML-coded text or URLs should be read out. The read-aloud function can also be limited to certain parts of the document.
• Individual configuration
  Voice Reader Server 22 TTS can be configured according to individual requirements, e.g. enter the maximum size of the http request, paths to the individual configuration files of the interfaces, defined lifetime of the individual audio files in the cache.
• High performance
  Voice Reader Server 22 TTS offers automatic conversion of text into voice output with a high data throughput (approx. × 4 reading tempo).

• Available in many languages with male and female voices
  Voice Reader Server 22 is available in 64 languages. The number in brackets refers to the number of voices supplied:

  Arabic (3)	Hebrew (1)	Russian (3)
  Arabic (Gulf Region) (1)	Hindi (3)	Swedish (3)
  Bengali (India) (1)	Indonesian (1)	Slovak(1)
  Bulgarian (1)	Italian (5)	Spanish (3)
  Croatian (1)	Japanese (7)	Spanish (Chile) (1)
  Basque (1)	Cantonese (Hongkong) (2)	Spanish (Colombian) (2)
  Danish (2)	Kannada (India) (1)	Spanish (Mexican) (3)
  German (5)	Catalan (2)	Spanish (Argentine) (2)
  English (American) (6)	Korean (5)	Tamil (1)
  English (Australian) (3)	Malay (1)	Telugu (1)
  English (British) (6)	Dongbei (China) (1)	Thai (2)
  English (Indian) (4)	Mandarin (China) (13)	Czech (2)
  English (Irish) (1)	Mandarin (Taiwan) (1)	Turkish (2)
  English (Scottish) (1)	Marathi (1)	Hungarian (1)
  English (South African) (1)	Dutch (Netherlands) (2)	Valencian (1)
  Finnish (2)	Dutch (Belgium) (1)	Persian (1)
  French (3)	Norwegian (2)	Vietnamese (1)
  French (Canadian) (3)	Polish (3)	Ukrainian (1)
  French (Belgium) (1)	Portuguese (3)	Slovenian (1)
  Galician (1)	Portuguese (Brazilian) (3)	Sichuanese (2)
  Greek (2)	Romanian (1)	Shanghainese (China) (1)

System requirements:

• Microsoft Windows Server 2022, 2019 or 2016, Windows 11 or 10
• Microsoft Internet Information Server