{"id":260971,"date":"2026-08-03T16:24:50","date_gmt":"2026-08-03T23:24:50","guid":{"rendered":"https:\/\/picsart.com\/blog\/?p=260971"},"modified":"2026-08-03T16:24:50","modified_gmt":"2026-08-03T23:24:50","slug":"all-about-grok-tts","status":"publish","type":"post","link":"https:\/\/picsart.com\/blog\/all-about-grok-tts\/","title":{"rendered":"All about the Grok text to speech model and how to use it"},"content":{"rendered":"
<\/figure>\r\n

Grok text to speech turns written text into spoken audio with a single API call, and the feature that separates it from a standard voice generator is control. Inline speech tags let you place a laugh, a whisper, or a pause exactly where you want one, so delivery stops being something you hope for and becomes something you write. xAI released it on April 17, 2026 alongside Grok Speech to Text, built on the same stack that runs Grok Voice, Tesla vehicles, and Starlink customer support.<\/p>\r\n

Grok TTS is available in the Picsart AI Playground<\/a>, so trying it takes a prompt rather than an API key. Every technical detail below comes from xAI’s own documentation.<\/p>\r\n

Grok text to speech at a glance<\/span><\/h2>\r\n\r\n
\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n
Spec<\/th>\r\nDetail<\/th>\r\n<\/tr>\r\n<\/thead>\r\n
Developer<\/td>\r\nxAI<\/td>\r\n<\/tr>\r\n
Released<\/td>\r\nApril 17, 2026<\/td>\r\n<\/tr>\r\n
Two ways in<\/td>\r\nA standard request for finished audio, or streaming for real time<\/td>\r\n<\/tr>\r\n
Max text<\/td>\r\n15,000 characters per standard request<\/td>\r\n<\/tr>\r\n
Languages<\/td>\r\n20, plus auto-detect<\/td>\r\n<\/tr>\r\n
Voices on Picsart<\/td>\r\n5<\/td>\r\n<\/tr>\r\n
Price via xAI<\/td>\r\n$15.00 per 1 million characters<\/td>\r\n<\/tr>\r\n
Price via Picsart<\/td>\r\n1 credit per 1,000 characters<\/td>\r\n<\/tr>\r\n<\/tbody>\r\n<\/table>\r\n<\/figure>\r\n\r\n

What is Grok text to speech?<\/span><\/h2>\r\n

Grok text to speech, also called Grok TTS, is a standalone audio API from xAI that converts text into spoken audio. It arrived as one half of a pair, with Grok Speech to Text handling transcription in the other direction, and it is aimed at voice agents, accessibility tools, podcasts, and interactive audio.<\/p>\r\n

There are two ways in. The standard one takes a block of text and hands back a finished audio file. The streaming one sends audio back while the text is still arriving, which is what live voice assistants need.<\/p>\r\n

Either way, the request is short. You supply the words, the language, and the voice, and audio comes back. Everything else has a sensible default.<\/p>\r\n

Two things are required: the words you want spoken, up to 15,000 characters, and the language they should be read in. Everything else is optional.<\/p>\r\n