This work presents na unrestricted text-to-speech synthesis system for brazilian portuguese. The system is based on the concatenation by rules of previously coded speech units. An extremely reduced set of synthesis units (149) is proposed. This set is mostly comprised of consonant-vowel (CV) transitions, which represent crucial acoustic segments in the speech production process. Production of highly intelligible speech is show to be possible through concatenation of these units. A CELP model is also proposed as a compression and synthesis structure, which includes necessary adaptations in order to modify the speech prosody during its decoding phase. Subjective tests showed that speech synthesized through the proposed CELP model is judged superior to that obtained through an LPC Vocoder (mono-pulse/noise excited), which is traditionally used in text-to-speech synthesis systems.