Meow

app.py

@@ -112,6 +112,7 @@ def main():
                 stt_input_mic = gr.Audio(source="microphone", type="filepath", label="Record")
                 stt_input_file = gr.Audio(source="upload", type="filepath", label="Upload")
             with gr.Column(variant="panel"):
+                stt_transcribe_output = gr.Textbox()
                 stt_transcribe_btn = gr.Button("Transcribe")
 
         def synthesize_audio(text_str: str, model_name_str: str, speaker_str: str):
@@ -140,7 +141,7 @@ def main():
             return gr.Audio.update(value=(tts.get_sampling_rate(), samples))
 
         generate.click(synthesize_audio, inputs=[text, model_name, speaker], outputs=audio, api_name="synthesize")
-        stt_transcribe_btn.click(transcribe_stt, inputs=stt_input_file, outputs=text, api_name="transcribe")
+        stt_transcribe_btn.click(transcribe_stt, inputs=stt_input_file, outputs=stt_transcribe_output, api_name="transcribe")
 
     demo.queue(concurrency_count=1).launch()