xai/grok-text-to-speech 📝❓✓ → 🖼️
Performance
3.1sTypical run time
859.8KTotal runs
About
Convert text to natural-sounding speech with xAI's Grok TTS. 5 voices, 20 languages, expressive speech tags, and high-fidelity MP3 / WAV / telephony audio output.
Example Output
Output
Performance Metrics
3.15s
Prediction Time
3.22s
Total Time
All Input Parameters
{
"text": "Hello! Welcome to Replicate's text-to-speech API. This is the Grok TTS model from xAI, generating natural and expressive speech.",
"voice": "eve",
"language": "en"
}
Input Parameters
- text (required)
- Text to synthesize into speech. Maximum 15000 characters. Supports inline speech tags like '[pause]', '[laugh]', and wrapping tags like '<whisper>...</whisper>' for expressive delivery.
- voice
- Voice to use for synthesis. 'eve' is energetic and upbeat (default), 'ara' is warm and friendly, 'rex' is confident and clear, 'sal' is smooth and balanced, 'leo' is authoritative and strong.
- bit_rate
- MP3 bit rate in bits per second. Only used when 'output_format' is 'mp3'. Higher bit rates produce better quality at the cost of file size.
- language
- BCP-47 language code for the input text. Set to 'auto' to let the model auto-detect the language.
- sample_rate
- Audio sample rate in Hz. Higher rates produce better quality at the cost of file size.
- output_format
- Audio codec. 'mp3' is best for general use, 'wav' for lossless audio, 'pcm' for raw audio pipelines, 'mulaw'/'alaw' for telephony.
- text_normalization
- Normalize written-form text (numbers, abbreviations, symbols) into spoken-form before generating audio.
Output Schema
Output
Example Execution Logs
Synthesized 128 chars to 155,520 bytes (mp3) in 2.8sec
Version Details
- Version ID
443e01eb52b1b778d289f279ef544b787eab857a8683fb1c0a02c2676306ce85- Version Created
- April 28, 2026