1.0

app.py

@@ -0,0 +1,217 @@
+import json
+import mimetypes
+import os
+import shutil
+import tempfile
+import time
+
+import assemblyai as aai
+import gradio as gr
+import numpy as np
+import requests
+import sounddevice as sd
+from elevenlabs import clone, generate, play, set_api_key, stream
+from scipy.io.wavfile import write
+
+set_api_key("cedcbf1991539f9c825a9346e1b7b708")
+import mimetypes
+
+from gradio.components import Audio, Radio, Textbox
+from gradio.components import Audio as AudioInput
+from gradio.components import Audio as AudioOutput
+from gradio.components import Textbox as TextboxOutput
+
+APP_KEY = "6lWL15cmmm5y5hLYU8-MvQ=="
+APP_SECRET = "xoXvx_qwuD5HczjnEYOC9OJj6HGCZDFZBHKHEegigHA="
+
+aai.settings.api_key = "6c7f4d60028e4df9b889b93acb8ed698"
+
+
+def transcribe_audio(file_path):
+    transcriber = aai.Transcriber()
+    transcript = transcriber.transcribe(file_path)
+    return transcript.text
+
+
+def clone_and_stream_voice(name, description, labels, text, model):
+    voice = clone(
+        name=name, description=description, files=["output.wav"], labels=labels
+    )
+
+    audio = generate(
+        text=text,
+        voice=voice,
+        model=model,
+        stream=True,
+        stream_chunk_size=2048,
+        latency=1,
+    )
+
+    stream(audio)
+
+
+def get_access_token():
+    payload = {"grant_type": "client_credentials", "expires_in": 1800}
+    response = requests.post(
+        "https://api.dolby.io/v1/auth/token",
+        data=payload,
+        auth=requests.auth.HTTPBasicAuth(APP_KEY, APP_SECRET),
+    )
+    return response.json()["access_token"]
+
+
+def upload_media(file_path, headers):
+    upload_url = "https://api.dolby.com/media/input"
+    upload_body = {"url": f"dlb://in/{os.path.basename(file_path)}"}
+    response = requests.post(upload_url, json=upload_body, headers=headers)
+    response.raise_for_status()
+    presigned_url = response.json()["url"]
+
+    with open(file_path, "rb") as input_file:
+        requests.put(presigned_url, data=input_file)
+
+
+def create_enhancement_job(file_path, output_path, headers, audio_type):
+    enhance_url = "https://api.dolby.com/media/enhance"
+    enhance_body = {
+        "input": f"dlb://in/{os.path.basename(file_path)}",
+        "output": f"dlb://out/{os.path.basename(output_path)}",
+        "content": {"type": audio_type},
+    }
+    response = requests.post(enhance_url, json=enhance_body, headers=headers)
+    response.raise_for_status()
+    return response.json()["job_id"]
+
+
+def check_job_status(job_id, headers):
+    status_url = "https://api.dolby.com/media/enhance"
+    params = {"job_id": job_id}
+    while True:
+        response = requests.get(status_url, params=params, headers=headers)
+        response.raise_for_status()
+        status = response.json()["status"]
+        if status == "Success":
+            break
+        print(f"Job status: {status}, progress: {response.json()['progress']}%")
+        time.sleep(5)
+
+
+def download_enhanced_file(output_path, headers):
+    download_url = "https://api.dolby.com/media/output"
+    args = {"url": f"dlb://out/{os.path.basename(output_path)}"}
+    with requests.get(
+        download_url, params=args, headers=headers, stream=True
+    ) as response:
+        response.raise_for_status()
+        response.raw.decode_content = True
+        print(f"Downloading from {response.url} into {output_path}")
+        with open(output_path, "wb") as output_file:
+            shutil.copyfileobj(response.raw, output_file)
+
+
+def dolby_process(input_file, output_file, audio_type):
+    access_token = get_access_token()
+    headers = {"Authorization": f"Bearer {access_token}"}
+    upload_media(input_file, headers)
+    job_id = create_enhancement_job(input_file, output_file, headers, audio_type)
+    check_job_status(job_id, headers)
+    download_enhanced_file(output_file, headers)
+
+
+def enhance_audio(recording, upload, audio_type):
+    audio_type = audio_type_mapping[audio_type]
+    if recording is not None:
+        rate, data = recording
+        temp_input_file = "input.wav"
+    elif upload is not None:
+        rate, data = upload
+        if rate not in [44100, 48000] or data.dtype not in [np.int16, np.int32]:
+            return None, None, "Invalid file type. Please upload an MP3 file."
+        temp_input_file = "input.mp3"
+    else:
+        return (
+            None,
+            None,
+            "Invalid input. Please record some audio or upload an audio file.",
+        )
+
+    write(temp_input_file, rate, data)
+
+    temp_output_file = "output.wav"
+    dolby_process(
+        temp_input_file, temp_output_file, audio_type
+    )  # Pass the audio type to the Dolby processing function
+
+    return temp_input_file, temp_output_file, "Processing complete!"
+
+
+def clone_voice(temp_output_file):
+    # Your voice cloning logic goes here
+    cloned_voice_file = "cloned_voice.wav"
+    return cloned_voice_file, "Voice cloning complete!"
+
+
+audio_type_mapping = {
+    "Conference": "conference",
+    "Interview": "interview",
+    "Lecture": "lecture",
+    "Meeting": "meeting",
+    "Mobile Phone": "mobile_phone",
+    "Music": "music",
+    "Podcast": "podcast",
+    "Studio": "studio",
+    "Voice Over": "voice_over",
+}
+
+from gradio import Checkbox
+
+
+def combined_function(
+    recording, upload, audio_type, proceed_to_clone, name, description, labels, model
+):
+    input_file, output_file, status1 = enhance_audio(recording, upload, audio_type)
+    status1 = "Enhancement complete!"
+    transcript = transcribe_audio(output_file)
+    if proceed_to_clone:
+        clone_and_stream_voice(name, description, labels, transcript, model)
+        status2 = "Cloning complete!"
+    else:
+        status2 = "Voice cloning not performed."
+    return input_file, output_file, status1, transcript, status2
+
+
+def main():
+    iface = gr.Interface(
+        fn=combined_function,
+        inputs=[
+            Audio(source="microphone", label="Recorded Audio"),
+            Audio(source="upload", label="Uploaded Audio"),
+            Radio(choices=list(audio_type_mapping.keys()), label="Audio Type"),
+            Checkbox(label="Proceed to Clone Voice"),
+            Textbox(label="Name"),
+            Textbox(label="Description"),
+            Textbox(label="Labels"),
+            Radio(
+                choices=["eleven_monolingual_v1", "eleven_multilingual_v1"],
+                label="Model",
+            ),
+        ],
+        outputs=[
+            Audio(type="filepath", label="Original Audio"),
+            Audio(type="filepath", label="Processed Audio"),
+            Textbox(label="Enhancement Status"),
+            Textbox(label="Transcript"),
+            Textbox(label="Cloning Status"),
+        ],
+        title="Audio Enhancer, Transcriber and Voice Cloner",
+        description="Enhance your audio, transcribe it and clone voices using the Dolby API",
+        allow_flagging="never",
+
+    )
+
+    iface.launch(server_name="0.0.0.0", server_port=7860,share=True)
+
+
+if __name__ == "__main__":
+
+    main()

requirement.txt

@@ -0,0 +1,117 @@
+aiofiles==23.1.0
+aiohttp==3.8.5
+aiosignal==1.3.1
+altair==5.0.1
+annotated-types==0.5.0
+anyio==3.7.1
+appnope==0.1.3
+assemblyai==0.15.1
+asttokens==2.2.1
+async-timeout==4.0.2
+attrs==23.1.0
+backcall==0.2.0
+black==23.7.0
+certifi==2023.7.22
+cffi==1.15.1
+charset-normalizer==3.2.0
+click==8.1.6
+contourpy==1.1.0
+cycler==0.11.0
+decorator==5.1.1
+elevenlabs==0.2.21
+executing==1.2.0
+fastapi==0.100.1
+ffmpeg-python==0.2.0
+ffmpy==0.3.1
+filelock==3.12.2
+fonttools==4.41.1
+frozenlist==1.4.0
+fsspec==2023.6.0
+future==0.18.3
+gradio==3.39.0
+gradio_client==0.3.0
+h11==0.14.0
+httpcore==0.17.3
+httpx==0.24.1
+huggingface-hub==0.16.4
+idna==3.4
+importlib-metadata==6.8.0
+ipython==8.14.0
+jedi==0.19.0
+Jinja2==3.1.2
+jsonschema==4.18.4
+jsonschema-specifications==2023.7.1
+kiwisolver==1.4.4
+linkify-it-py==2.0.2
+llvmlite==0.40.1
+markdown-it-py==2.2.0
+MarkupSafe==2.1.3
+matplotlib==3.7.2
+matplotlib-inline==0.1.6
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+more-itertools==10.0.0
+mpmath==1.3.0
+multidict==6.0.4
+mypy-extensions==1.0.0
+networkx==3.1
+numba==0.57.1
+numpy==1.24.4
+openai-whisper==20230314
+orjson==3.9.2
+packaging==23.1
+pandas==2.0.3
+parso==0.8.3
+pathspec==0.11.2
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==10.0.0
+platformdirs==3.10.0
+prompt-toolkit==3.0.39
+ptyprocess==0.7.0
+pure-eval==0.2.2
+PyAudio==0.2.13
+pycparser==2.21
+pydantic==1.10.12
+pydantic_core==2.4.0
+pydub==0.25.1
+Pygments==2.15.1
+pyparsing==3.0.9
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytz==2023.3
+PyYAML==6.0.1
+referencing==0.30.0
+regex==2023.6.3
+requests==2.31.0
+rich==13.5.0
+rpds-py==0.9.2
+safetensors==0.3.1
+scipy==1.11.1
+semantic-version==2.10.0
+setuptools-rust==1.6.0
+six==1.16.0
+sniffio==1.3.0
+sounddevice==0.4.6
+SpeechRecognition==3.10.0
+stack-data==0.6.2
+starlette==0.27.0
+sympy==1.12
+tdqm==0.0.1
+tiktoken==0.3.1
+tokenizers==0.13.3
+toolz==0.12.0
+torch==2.0.1
+tqdm==4.65.0
+traitlets==5.9.0
+transformers==4.31.0
+typing_extensions==4.7.1
+tzdata==2023.3
+uc-micro-py==1.0.2
+urllib3==2.0.4
+uvicorn==0.23.1
+wcwidth==0.2.6
+websockets==11.0.3
+whisper-mic==1.1.1
+yarl==1.9.2
+zipp==3.16.2