Text-to-Speech
Safetensors
English
steertts
steer-tts
tts
speech-synthesis
english
controllable-tts
steerable-tts
prosody-control
expressive-tts
style-control
inline-markup
word-emphasis
zero-shot-voice-cloning
voice-cloning
interpretable
non-autoregressive
fastpitch
mamba
mamba-3
state-space-model
hybrid-attention
flow-matching
vocos
small-model
quantized
int8
on-device
streaming
non-commercial
Eval Results (legacy)
| import os | |
| from pathlib import Path | |
| import pytest | |
| MODEL = os.environ.get("STEERTTS_MODEL") or str(Path(__file__).resolve().parents[1]) | |
| DEV = os.environ.get("STEERTTS_TEST_DEVICE", "cpu") | |
| def model_dir(): | |
| if not (Path(MODEL) / "config.json").exists(): | |
| pytest.skip(f"no model directory at {MODEL} (set STEERTTS_MODEL)") | |
| return MODEL | |
| def tts(model_dir): | |
| from steertts import SteerTTS | |
| return SteerTTS(model_dir, device=DEV, flow=False) | |
| def tts_flow(model_dir): | |
| from steertts import SteerTTS | |
| return SteerTTS(model_dir, device=DEV) | |