Create app.py

app.py

@@ -0,0 +1,124 @@
+import os
+import gradio as gr
+import outetts
+from outetts.version.v2.interface import _DEFAULT_SPEAKERS
+
+model_config = outetts.HFModelConfig_v2(
+    model_path="OuteAI/OuteTTS-0.3-1B",
+    tokenizer_path="OuteAI/OuteTTS-0.3-1B",
+)
+interface = outetts.InterfaceHF(model_version="0.3", cfg=model_config)
+
+def get_available_speakers():
+    speakers = list(_DEFAULT_SPEAKERS.keys())
+    return speakers
+
+def generate_tts(
+        text, temperature, repetition_penalty,
+        speaker_selection, reference_audio
+    ):
+    """Generate TTS with error handling and new features."""
+    try:
+        # Validate inputs for custom speaker
+        if reference_audio:
+            speaker = interface.create_speaker(reference_audio)
+
+        # Use selected default speaker
+        elif speaker_selection and speaker_selection != "None":
+            speaker = interface.load_default_speaker(speaker_selection)
+
+        # No speaker - random characteristics
+        else:
+            speaker = None
+
+        gen_cfg = outetts.GenerationConfig(
+            text=text,
+            temperature=temperature,
+            repetition_penalty=repetition_penalty,
+            max_length=4096,
+            speaker=speaker,
+        )
+        output = interface.generate(config=gen_cfg)
+
+        # Verify output
+        if output.audio is None:
+            raise ValueError("Model failed to generate audio. This may be due to input length constraints or early EOS token.")
+
+        # Save and return output
+        output_path = "output.wav"
+        output.save(output_path)
+        return output_path, None
+
+    except Exception as e:
+        return None, str(e)
+
+with gr.Blocks() as demo:
+    gr.Markdown("# OuteTTS-0.3-1B Text-to-Speech Demo")
+
+    error_box = gr.Textbox(label="Error Messages", visible=False)
+
+    with gr.Row():
+        with gr.Column():
+
+            # Speaker selection
+            speaker_dropdown = gr.Dropdown(
+                choices=get_available_speakers(),
+                value="en_male_1",
+                label="Speaker Selection"
+            )
+
+            text_input = gr.Textbox(
+                label="Text to Synthesize",
+                placeholder="Enter text here..."
+            )
+
+            temperature = gr.Slider(
+                0.1, 1.0,
+                value=0.1,
+                label="Temperature (lower = more stable tone, higher = more expressive)"
+            )
+
+            repetition_penalty = gr.Slider(
+                0.5, 2.0,
+                value=1.1,
+                label="Repetition Penalty"
+            )
+
+            gr.Markdown("""
+### Voice Cloning Guidelines:
+- Use around 7-10 seconds of clear, noise-free audio
+- For transcription interface will use Whisper turbo to transcribe the audio file
+- Longer audio clips will reduce maximum output length
+- Custom speaker overrides speaker selection
+            """)
+
+            reference_audio = gr.Audio(
+                label="Reference Audio (for voice cloning)",
+                type="filepath"
+            )
+
+            submit_button = gr.Button("Generate Speech")
+
+        with gr.Column():
+            audio_output = gr.Audio(
+                label="Generated Audio",
+                type="filepath"
+            )
+
+    submit_button.click(
+        fn=generate_tts,
+        inputs=[
+            text_input,
+            temperature,
+            repetition_penalty,
+            speaker_dropdown,
+            reference_audio,
+        ],
+        outputs=[audio_output, error_box]
+    ).then(
+        fn=lambda x: gr.update(visible=bool(x)),
+        inputs=[error_box],
+        outputs=[error_box]
+    )
+
+demo.launch()