-
Language: English ›
- American English British English British English Polski - Polish Polski - Polish
IVONA Telecom – Technical specification
PDF
|
|
IVONA Telecom MRCP
|
IVONA Telecom SAPI
|
IVONA Telecom Asterisk
|
||||||
|---|---|---|---|---|---|---|---|---|---|
|
Requirements
| |||||||||
|
CPU requirements
|
X86 (32/64bit), Sparc*
|
X86 (32/64bit)
|
X86 (32/64bit), Sparc*
| ||||||
|
Recommended configurations
|
1 Depending on used voice/language
| ||||||||
|
OS
|
Linux, Solaris*, Mac OSX*, Windows***, Windows Server***
|
Windows, Windows Server
|
Linux, Solaris*
| ||||||
|
Interfaces
|
MRCP v1 (RFC 4463), MRCP v2, command line, UniMRCP*
|
SAPI 5, SAPI 4*, command line
|
Command line
| ||||||
|
Standards compliance
|
W3C SSML 1.0/1.1, W3C PLS 1.0 (with IVONA extensions)
|
W3C SSML 1.0/1.1, W3C PLS 1.0 (with IVONA extensions), SAPI markup (with support for mixing with SSML tags)
|
W3C SSML 1.0/1.1, W3C PLS 1.0 (with IVONA extensions)
| ||||||
|
Supported platforms
|
|
All SAPI compatible platforms
|
Asterisk versions:
1.2, 1.4, 1.6, 1,8 | ||||||
|
Key features
| |||||||||
|
BrightVoice™: superior speech output quality
|
|
|
| ||||||
|
Languages and voices
|
US English (2 male, 3 female, child); British English (male, 2 female); US Spanish (male, female, child**); Spanish (male, female, child**); German (male, female); French (male, female); Polish (2 male, 2 female); Romanian (female); Welsh; Welsh English; Australian English**; Italian**; Dutch**; Canadian French**; Brazilian Portuguese**; Portuguese**; Icelandic**; Russian**; Korean**; Danish**; Swedish**; Japanese**; Special Effects (SFX)/Character voices*
| ||||||||
|
Sampling rate
|
8 kHz, 22 kHz (up to 48 kHz*)
| ||||||||
|
Audio formats
|
A-law, μ-law, PCM 16 bit mono/stereo*
|
A-law, μ-law, PCM 16 bit mono/stereo*
|
A-law, μ-law, PCM 16 bit mono
| ||||||
|
Components
|
Media Server (MRCP), speech server, tools, documentation
|
SAPI component, tools, documentation
|
Asterisk plugin, speech server, tools, documentation
| ||||||
|
Scalability by multiplying speech servers
|
|
|
**
| ||||||
|
Low response (start/stop and barge-in) time
|
|
|
| ||||||
|
Prosody control: volume, speed, pitch
|
|
|
| ||||||
|
User level pronunciation lexicon
|
(with regular expression rules support) |
|
| ||||||
|
Language detection
|
**
|
**
|
**
| ||||||
|
Phoneme mapping for mixed languages input
|
**
|
**
|
**
| ||||||
|
Text preprocessing rules for specific domains
|
*
|
*
|
*
| ||||||
|
Dynamic voice and language switching
|
|
|
| ||||||
|
Mixing static expressive prompts
|
|
|
| ||||||
|
Custom voices: voice branding or custom accent and/or style
|
|
|
| ||||||
|
Support for phonetic alphabets
|
IPA, X-SAMPA, TeleAtlas®, Navteq™
|
IPA, X-SAMPA, TeleAtlas®, Navteq™
|
IPA, X-SAMPA, TeleAtlas®, Navteq™
| ||||||
|
Expressive TTS effects
|
**
|
**
|
| ||||||
|
Contrast (feature to extract speech from background noise)
|
**
|
**
|
**
| ||||||
|
Support of requests peaks handling
|
**
|
**
|
**
| ||||||
* Available on request
** Feature in development
*** Using UniMRCP
** Feature in development
*** Using UniMRCP
Examples of implementations
The quality of the IVONA brand is not only evidenced by our numerous awards and honors. We are especially proud of the large number of business partners who have placed their trust in us. More
