VOice, REliable and RObust
HOME > Text-to-speech middleware > About VOStalk
Text-to-speech middleware
About VOStalk

VOStalk is a compact Japanese-language TTS engine based on Asahi Kasei voice technology. It features high-quality sound and natural prosody with low processor load and low memory requirements.
  Features
 
High quality sound and natural prosody
Low memory size required
Low processor load
Adjustable voice sound and prosody

Direct Phrasing function enables arbitrary adjustment of prosody
Pitch, volume, speed, and spectrum may be changed dynamically
Equalizing function available

Voice customizing available
Japanese TTS in two stages

Text to intermediate expression (TTI) engine and intermediate expression to speech (ITS) engine
Operating system independent engine source code with object-oriented design

Vocabulary rich lexicon for text analysis
Two-way text input enabled

Mixture of kanji, kana, and digits
Intermediate expression (pronunciation with accent information)

Support for 11.025 KHz and 22.05 KHz sampling rates

  Platforms
 
VOStalk TTS middleware is not dependent on any specific RTOS

Windows 2000/XP
Linux, μ-iTRON
Micro-controllers (ARM, SH, MIPS), Pentium-compatible CPUs

    go to top
News
Voice recognition middleware
VORERO
Text-to-speech middleware
VOStalk
Hands free middleware
VOCLE
Voice compression / decompression middleware
MMEV
SpeechSolutions
Asahi KASEI
Japanese Contact us HOME Site map