Models & PricingModel Cards
March 30, 2026
GAPREMIERv26.03
Sonus TTS
State-of-the-art text-to-speech with zero-shot voice cloning and multilingual support. Hyper-realistic speech with fine-grained emotion control.
Speed
Performance
Context
4k chars
Price
$15.00 / $30.00 /1M chars
Features
Features
Try it
import sagea
client = sagea.Client(api_key="your-api-key")
audio = client.audio.speech.create(
model="sonus-tts",
input="Welcome to SAGEA. Engineering intelligence that feels alive.",
voice="nova",
response_format="mp3"
)
audio.stream_to_file("output.mp3")Base URL: https://api.sagea.space/v1 — Auth: Authorization: Bearer $SAGEA_API_KEY
Specifications
| Supported Languages | 30+ |
| Max Input Length | 4,096 characters |
| Audio Formats | MP3, WAV, OGG, FLAC |
| Sample Rates | 16kHz, 24kHz, 44.1kHz |
| Latency | < 200ms first byte |
Other Models
Capabilities
Sonus TTS is SAGEA's state-of-the-art text-to-speech model with zero-shot voice cloning. It supports 30+ languages, streaming with ~200ms time-to-first-audio, and no transcript required for voice prompts.
- Zero-shot cloning: clone from a 10-second sample via
POST https://api.sagea.space/v1/audio/clone. - Multilingual: native-quality pronunciation across 30+ languages.
- Emotion control: real-time emotion shifting (
neutral,friendly,professional,excited,calm,warm). - Streaming:
POST https://api.sagea.space/v1/audio/streamfor conversational AI.
Benchmarks
| Metric | Value |
|---|---|
| Naturalness (MOS) | 4.6 / 5.0 |
| Time-to-first-audio | ~200ms |
| Languages | 30+ |
| Formats | MP3, WAV, OGG, FLAC (16 / 24 / 44.1 kHz) |
Use cases
- Voice assistants and conversational agents
- Media narration and accessibility
- Branded custom voices
Limitations
- Max 4,096 characters per synthesis request — chunk long documents.
- Cloned voices are billed at $30.00 / 1M chars. See Choosing a Model.
Next steps
- Voice synthesis quickstart
- Voice cookbooks: cloning, streaming, audiobooks, IVR packs
- API Reference