Introduction

​

Why Nineninesix?

• Fastest: Ultra-low-latency streaming for sub-second time-to-first-audio, so conversations feel instant
• Most human-like: Dialogue-native voices trained on real conversational speech — natural prosody, pacing, and emotion, not flat long-form narration
• Real-time by design: Batch (/tts/bytes), Server-Sent Events (/tts/sse), and low-latency WebSocket (/tts/websocket) streaming
• Simple billing: 1 credit per character, $5 per 1M characters, credits never expire

​

Quick Example

curl -N https://api.nineninesix.ai/tts/bytes \
  -H "Authorization: Bearer sk_996_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "gepard-1.0",
    "transcript": "Hello world! This is Nineninesix.",
    "voice": { "mode": "id", "id": "<voice-id>" },
    "output_format": { "container": "wav", "encoding": "pcm_s16le", "sample_rate": 22050 }
  }' --output speech.wav

​

Next Steps