text_to_speech

click.ciromaciel/tools · Verify this server

Reads a text aloud with a Microsoft neural voice (the voices of Edge's "Read aloud") and returns an MP3. WHEN TO USE: the user wants to hear a text or needs an audio file of it — narration, audiobook, lesson, voice-over, a message read aloud. HOW IT WORKS: - Up to 50,000 characters per call. A text over 1,000 characters is split by sentence into parts of up to 1,000; each part is voiced in order and the parts are joined into ONE MP3. Progress is reported per part ("Gerando áudio... 3 de 18"), so keep waiting while it arrives. - It takes time: about 5 seconds per part. 5,000 characters ≈ 30 s; 16,000 ≈ 2 min; 50,000 ≈ 6 min. - Over 50,000 characters: split the text at paragraph boundaries into several calls with the same voice and speed, and give the user every link, in order. - Send the text as it should be HEARD: remove Markdown marks (**, #, list bullets), URLs, emojis and tables. Do not summarize, translate or reword unless the user asked — every word you send is read. - voice: choose one in the language of the text (the prefix is language-region: pt-BR, pt-PT, en-US, es-MX…). Brazilian Portuguese: pt-BR-FranciscaNeural (female, default) or pt-BR-AntonioNeural (male). - speed: 1 is the voice's natural pace; 0.9 suits calm narration, 1.2 a quick read. RETURNS: - audioUrl: the complete MP3 to download, valid for 7 days. Always give this link to the user. If you can run commands, you can download it (e.g. curl -o audio.mp3 <audioUrl>). - audio: the MP3 itself, only when it is short (about 1.5 minutes or less); otherwise null. - seconds (duration), parts, characters, voice, speed. - link: this tool's web page with the same voice and speed (the text is not in it). ERRORS say what happened and what to do next. If a part fails, no audio is produced and a new call starts again from part 1.