Try Audio

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import pipeline
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
@@ -7,6 +8,8 @@ For more information on `huggingface_hub` Inference API support, please check th
 
 client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
 
+tts = pipeline("text-to-speech", model="facebook/tts_transformer-EN-GLACIAL")
+
 
 def respond(
     message,
@@ -40,6 +43,9 @@ def respond(
         response += token
         yield response
 
+    audio = tts(response)
+    return response, audio
+
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -58,6 +64,7 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    outputs=[gr.Textbox(), gr.Audio()],
 )
 
 

requirements.txt

@@ -1,3 +1,4 @@
 huggingface_hub
 unsloth
 gradio
+transformers