Aimesoft Updates Its Aimespeech TTS

Aimesoft has released a new version of its text-to-speech (TTS) engine, part of its Aimespeech speech processing framework.

The new version of the TTS engine applies the latest prosody modeling techniques that make natural voice outputs with better word-level emphasis. When reading long sentences, the engine produces better intonation and handles automatic pauses appropriately.

AimeSpeech TTS engine learns human voices and artificially creates human voices with tone and intonation similar to those of humans. It is the core speech processing framework inside the Aimenicorn software ecosystem from Aimesoft and includes speech recognition, speech synthesis engine, a speaker identification library, and other advanced speech processing libraries.

Besides the prosodic features, AimeSpeech TTS also converts notations and graphemes across languages to aid in the pronunciation of foreign language names, locations, and proper nouns. It serves as the basis of Aimesoft's AimeTalk virtual presenter software, AimeHotel virtual hotel clerk software, AimeReception virtual receptionist software, and AimeAIShop virtual shop clerk software.