Grok TTS
GAText-to-speech model, and the only row in this catalog billed per character, so the token price fields are null by design. xAI publishes the rate on its pricing page as $15.00 / 1M chars under 'Voice API', i.e. $0.000015 per character, and the models-index hydration payload carries the same figure as an integer in the 1e-10 USD units this catalog calibrated against two rows it already held: 'pricing': {'perCharacter': '150000'}. Input is text, output is audio - there is no token accounting on either side, so a caller budgets by character count, not by tokens. Request limits, from the reference: maximum 60,000 characters of text per request; voice_id defaults to 'eve'; a BCP-47 language code is required and 'auto' enables detection; output defaults to MP3 at 24 kHz / 128 kbps, with telephony-optimised mu-law among the other formats; speech tags control delivery inline. Custom voices cloned from a short clip can be used here and with the Speech to Speech API. Rate limits at the base tier are 50 rps / 3,000 rpm / 100 concurrent sessions, rising to 1,000 rps / 60,000 rpm at tier 5. RELEASED IS NULL AS A SOURCED ABSENCE, NOT A MISSING FIELD: xAI's release notes date the Text-to-Speech API going generally available to 2026-03-16 ('The Text-to-Speech API is now generally available'), but that entry does not name this model slug, and no release-notes entry anywhere on the page does - so the API has a first-party date and the model does not. Added to the catalog 2026-09-19 as a completeness fix; xAI published nothing on this date.
Grok TTS by xAI is tracked live in our LLM catalog. It is generally available (GA).
Last verified: 26 Sep 2026 · sourced from official provider documentation
◎ You're on the watch list. We'll ping you the moment a model launches, changes price, or gets deprecated.
✕ Couldn't subscribe right now — please try again in a moment.
Free forever · no spam · unsubscribe anytime.
Source: xAI official documentation ↗
Grok TTS — questions & answers
Is Grok TTS deprecated?
No — Grok TTS is generally available (GA) and not currently scheduled for deprecation or retirement in our tracker.
Does Grok TTS support image or vision input?
Our catalog lists Grok TTS's modalities as text-in, audio-out; image/vision input is not among them.
Can I self-host Grok TTS?
No — Grok TTS is proprietary. Its weights are not publicly released, so it is available only through xAI's API (or hosted partners), not for self-hosting.
What is the API model string for Grok TTS?
The API model identifier for Grok TTS is "grok-tts" when calling xAI's API.
Track Grok TTS price & status changes
New models, price cuts, and deprecations — a short email when something actually changes. No spam, unsubscribe anytime.
The last few changes we caught — this is what lands in your inbox:
- DeprecatingGoogle re-pointed the Gemini 2.5 TTS migration path past the 3.1 preview and onto the new GA 3.8 TTS models
- New modelGemini 3.8 Flash TTS is GA - a flagship text-to-speech model at under half the audio rate of the preview it replaces, on a two-column price schedule
- New modelGemini 3.8 Flash-Lite TTS is GA - Google's cost-efficient TTS, which Google says was built to replace Gemini 3.1 Flash TTS
◎ You're on the watch list. We'll ping you the moment a model launches, changes price, or gets deprecated.
✕ Couldn't subscribe right now — please try again in a moment.
Free forever · powered by the same data on this page.