gTTS

TextSpeech Pro is a professional text-to-speech software product, proudly awarded "the best text to speech software in the world". Synthesize text-to-speech from any document format (text, Microsoft Word, PDF, Microsoft Excel, RTF, etc) using a variety of voices and languages. Export the synthesized speech from documents to a variety of audio file formats in three modes (quick, normal and batch). Create and modify conversations, bookmarks and pauses (silence breaks) in a document using an advanced text-to-speech editor. Modify speech properties (voice, speed, volume, pitch, word highlighting) and speech entities (bookmarks, conversations, pauses) on the fly. Extract text from scanned documents and convert it to speech or audio files. Use a fully featured document editor with many text processing features (text manipulation, spell checker, print and print preview, find and replace, go to line, customizable fonts, zoom capabilities, and document properties view).

Sonic is a real-time text-to-speech model built for voice agents, combining natural delivery, sub-90ms latency, and native support for more than 40 languages. It is designed to make voice interactions feel effortless, with tone that adjusts to context, consistent pacing, and speech that follows the natural rhythm of conversation. By default, Sonic interprets the emotional subtext of a transcript and calibrates delivery automatically, while non-verbal expressions such as laughter can be inserted directly into the text. The model follows transcripts faithfully, produces clean audio across languages and voices, and handles alphanumeric content such as order numbers, phone numbers, IDs, and email addresses naturally without preprocessing. Context-aware pronunciation helps heteronyms sound correct from surrounding words, while custom pronunciation dictionaries let teams define how proper nouns and domain-specific terms should be spoken.