Instructions to use OuteAI/Llama-OuteTTS-1.0-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OuteTTS
How to use OuteAI/Llama-OuteTTS-1.0-1B with OuteTTS:
import outetts enum = outetts.Models("OuteAI/Llama-OuteTTS-1.0-1B".split("/", 1)[1]) # VERSION_1_0_SIZE_1B cfg = outetts.ModelConfig.auto_config(enum, outetts.Backend.HF) tts = outetts.Interface(cfg) speaker = tts.load_default_speaker("EN-FEMALE-1-NEUTRAL") tts.generate( outetts.GenerationConfig( text="Hello there, how are you doing?", speaker=speaker, ) ).save("output.wav") - Notebooks
- Google Colab
- Kaggle
Does anyone know good way make this open ai comparable speech api
#4
by TheMindExpansionNetwork - opened
Hello I am really impressed and trying to find solution to use for livekit I would like to see if there is way to host inference and make it open ai speech capable for webrtc server
use prebuilt libraries that can load transformers models or gguf models and voila you have it.
Hi,
You could wrap the outetts library with something like Flask or FastAPI with compatible request types. There are plans to implement server in the future for the outetts library.