Code

app.py

@@ -1,33 +1,55 @@
-import httpx
-
 import gradio as gr
+import httpx
 from gradio_dialogue import Dialogue
 
-emotions = ["(laughs)", "(clears throat)", "(sighs)", "(gasps)", "(coughs)", "(singing)", "(sings)", "(mumbles)", "(beep)", "(groans)", "(sniffs)", "(claps)", "(screams)", "(inhales)", "(exhales)", "(applause)", "(burps)", "(humming)", "(sneezes)", "(chuckle)", "(whistles)"]
+emotions = [
+    "(laughs)",
+    "(clears throat)",
+    "(sighs)",
+    "(gasps)",
+    "(coughs)",
+    "(singing)",
+    "(sings)",
+    "(mumbles)",
+    "(beep)",
+    "(groans)",
+    "(sniffs)",
+    "(claps)",
+    "(screams)",
+    "(inhales)",
+    "(exhales)",
+    "(applause)",
+    "(burps)",
+    "(humming)",
+    "(sneezes)",
+    "(chuckle)",
+    "(whistles)",
+]
 speakers = ["Speaker 1", "Speaker 2"]
 
-client  = httpx.AsyncClient(timeout=180)
+client = httpx.AsyncClient(timeout=180)
 
 
 async def query(dialogue: str, token: gr.OAuthToken | None):
     if token is None:
-        raise gr.Error("No token provided. Use Sign in with Hugging Face to get a token.")
+        raise gr.Error(
+            "No token provided. Use Sign in with Hugging Face to get a token."
+        )
     API_URL = "https://router.huggingface.co/fal-ai/fal-ai/dia-tts"
     headers = {
         "Authorization": f"Bearer {token.token}",
     }
-    print("Dialogue: ", dialogue)
-    dialogue = dialogue.replace("\n", " ")
-    print("Dialogue After: ", dialogue)
     response = await client.post(API_URL, headers=headers, json={"text": dialogue})
     url = response.json()["audio"]["url"]
     print("URL: ", url)
     return url
 
+
 def formatter(speaker, text):
     speaker = speaker.split(" ")[1]
     return f"[S{speaker}]: {text}"
 
+
 with gr.Blocks() as demo:
     with gr.Sidebar():
         login_button = gr.LoginButton()
@@ -42,23 +64,44 @@ with gr.Blocks() as demo:
     )
     with gr.Row():
         with gr.Column():
-            dialogue = Dialogue(speakers=speakers, emotions=emotions,
-                                formatter=formatter)
+            dialogue = Dialogue(
+                speakers=speakers, emotions=emotions, formatter=formatter
+            )
         with gr.Column():
             with gr.Row():
                 audio = gr.Audio(label="Audio")
             with gr.Row():
                 gr.DeepLinkButton(value="Share Audio via Link")
     with gr.Row():
-        gr.Examples(examples=[
-            [[{"speaker": "Speaker 1", "text": "Why did the chicken cross the road?"},
-             {"speaker": "Speaker 2", "text": "I don't know!"},
-             {"speaker": "Speaker 1", "text": "to get to the other side! (laughs)"}]],
-             [[{"speaker": "Speaker 1", "text": "(sighs) I am a little tired today."},
-             {"speaker": "Speaker 2", "text": "Hang in there!"},
-             ]]], inputs=[dialogue], cache_examples=False)
+        gr.Examples(
+            examples=[
+                [
+                    [
+                        {
+                            "speaker": "Speaker 1",
+                            "text": "Why did the chicken cross the road?",
+                        },
+                        {"speaker": "Speaker 2", "text": "I don't know!"},
+                        {
+                            "speaker": "Speaker 1",
+                            "text": "to get to the other side! (laughs)",
+                        },
+                    ]
+                ],
+                [
+                    [
+                        {
+                            "speaker": "Speaker 1",
+                            "text": "(sighs) I am a little tired today.",
+                        },
+                        {"speaker": "Speaker 2", "text": "Hang in there!"},
+                    ]
+                ],
+            ],
+            inputs=[dialogue],
+            cache_examples=False,
+        )
 
     dialogue.submit(query, [dialogue], audio)
 
 demo.launch(ssr_mode=False)
-

requirements.txt

@@ -1 +1 @@
-gradio-dialogue>=0.0.3
+gradio-dialogue>=0.0.4