---
title: VoXtream
emoji: ⚡
colorFrom: green
colorTo: yellow
sdk: gradio
python_version: 3.10
sdk_version: 4.44.1
app_file: app.py
pinned: true
license: cc-by-4.0
short_description: Generate speech from text and an audio prompt
models:
  - herimor/voxtream
tags:
  - text-to-speech
  - speech-synthesis
preload_from_hub:
  - herimor/voxtream model.safetensors,config.json,phoneme_to_token.json
  - kyutai/moshiko-pytorch-bf16 tokenizer-e351c8d8-checkpoint125.safetensors
  - charsiu/en_w2v2_fc_10ms pytorch_model.bin,config.json
  - charsiu/tokenizer_en_cmu special_tokens_map.json,tokenizer_config.json,vocab.json
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference