Text-to-Speech
Safetensors
GGUF
qwen2
audio
speech
speech-language-models
conversational

Is it supports RealTime Streaming Text to speech or not?

#3
by ApurvCodiste - opened

This model supports real time streaming or not?

Hey, keep an eye on github on streaming - we couldn't get the streaming code fit into the release but it's definitely possible to output chunks and stitch them together!

Hey, keep an eye on github on streaming - we couldn't get the streaming code fit into the release but it's definitely possible to output chunks and stitch them together!

sure, will wait πŸ‘

Hey, we just merged our streaming code! Can find the sample here: https://github.com/neuphonic/neutts-air/tree/main/examples#streaming-support

https://github.com/Edward-Zion-Saji/neutts-openai-api

Made streaming openai api compatible, just need to replace the base URL. Can quickly integrate with pipecat, livekit, openwebui

harryjulian changed discussion status to closed

Sign up or log in to comment