Model specifications
- Context
- 15,000 tokens
- Maximum output
- 13,500 tokens
- Architecture
- text->speech
- Tokenizer
- Grok
- Knowledge cutoff
- Not provided
- Moderated
- No
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Characters
- $15 per million characters
Model configuration
Supported voices
Quick start
Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.
Choose a supported voice. Replace YOUR_VOICE_ID if no voice is listed.
curl --fail-with-body https://openrouter.ai/api/v1/audio/speech \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"x-ai/grok-voice-tts-1.0","input":"Hello!","voice":"eve","response_format":"mp3"}' \
--output speech.mp3Input → Output
Supported API parameters
1 Provider
Checked: September 16, 2026
Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
xAI
Not provided- Context
- 15K
- Maximum output
- 14K