xAI: Grok Text to Speech
xai/grok-tts
active
tts
1 provider
xAI's Grok text-to-speech: converts text into spoken audio with 26 expressive voices, inline speech tags and output formats from high-fidelity MP3 to telephony-optimized mu-law, selected by endpoint (/v1/tts) rather than by a model parameter.
AuthorxAI
Languages1 languages
VoicesLoading...
Response formatsMP3 · WAV · PCM · µ-law · A-law
Statusactive
Providers
Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.
ProviderSlugPer 1k charactersLatencyiFor TTS, latency is measured as time to first byte of audio. For STT, latency is measured as time to first token.ModesUptime
xAI
5 params
grok
$0.015
—
Synchronous · Streaming
Supported languages
1 languages
English
en
Voices
Features
Text to speech
Generates spoken audio from text input.
text_to_speech
Streaming
Bidirectional streaming TTS over WebSocket (wss://api.x.ai/v1/tts).
streaming
Synchronous
Synthesizes speech from fully-submitted text in a single synchronous request.
synchronous
Multilingual
Supports 20 languages (BCP-47) plus automatic detection.
multilingual
Inline speech tags
Supports inline speech tags for expressive control.
speech_tags
Code
ElevenLabs SDK streaming TTS
Routes the ElevenLabs SDK through allmodels and streams the audio response.
import { ElevenLabsClient } from "elevenlabs";
const client = new ElevenLabsClient({
apiKey: process.env.ALLMODELS_API_KEY,
baseUrl: "https://api.allmodels.io/el"
});
const stream = await client.textToSpeech.stream("voice_id", {
text: "I'm sorry, Dave. I'm afraid I can't do that.",
modelId: "xai/grok-tts",
outputFormat: "mp3_44100_128"
}, {
queryParams: {
provider: {
"only": [
"grok"
]
}
}
});
const reader = stream.getReader();
for (;;) {
const { done, value } = await reader.read();
if (done) break;
// Write value to your response, file, or audio playback pipeline.
}