Leading developer of embedded voice solutions driving interaction with applications, and smart devices

FonixTalk TTS- Medium Footprint Text to Speech


FonixTalk is the world’s most intelligible text-to-speech (TTS) synthesizer, now with more natural sounding voices. Fonix-Talk has the smallest memory footprint in the industry for a full featured, multi-language voice synthesizer. FonixTalk’s small footprint allows it to be used in devices where a TTS engine usually wouldn't be viable. Click Here for info on DecTalk.


FonixTalk 6.1 comes with an easy to use API, as well as Microsoft's Speech API, so you can give your application the power of speech. FonixTalk has more than 1,400 letter-to-sound rules, as well as extensive text preprocessing to correctly speak monetary text like: $1.25, or clock times: 12:31 pm, or dates: Jan. 1, 2004, and even phone numbers: 800-297-4863. It has other important features:



• FonixTalk  supports nine languages: U.S. & U.K. English, Castilian & Latin American Spanish, German, French, and Italian.

• Dialect support for Castilian and Latin American Spanish, US & UK English.

• Asian language support for Korean and Mandarin Chinese. Contact Sales for Japanese.



• FonixTalk 6.1 offers nine voices: Paul, Betty, Harry, Dennis, Frank, Ursula, Rita, Wendy, and Kit, the industry's first child voice.

• Change voices and/or languages on demand.

• Create custom voices (less than 0.5 kb per voice).


High quality speech:

Represents the latest in speech synthesis technology.

• Requires only a standard sound card for audio output.

• Programmatically controls voice pitch, rate of speech, and word/phrase emphasis.

• Improved intelligibility at fast speaking rates.


Word pronunciation accuracy:

• Comes with a large built-in dictionary for accurate pronunciation of individual words (enhances rhythmic naturalness).

• Accurately reads ASCII text from a variety of sources, including electronic mail and word processors.


Letter, word and clause modes:

• Provides normal clause buffering for natural speech.

• Speaks letters, words, phrases, clauses, paragraphs, and even whole documents.

• Speaks single characters immediately (doesn't have to buffer an entire clause).

• Can terminate speech immediately (buffered text doesn't have to complete processing).


Pronunciation heuristics:

• Recognizes and pronounces non-word sequences

• Recognizes sequences with uppercase initials (e.g., FBI and AAA) and sequences without vowels (e.g., CBS and NBC).


FonixTalk Spec Sheet

FonixTalk SDK Demo

RealVoice TTS

DecTalk TTS

Contact Us

Copyright 2013 SpeechFX, Inc.