Merge pull request #17 from lfnovo/podcast2

Enable gemini text to speech model for podcast generation

README.md

@@ -87,10 +87,7 @@ Learn more about our project at [https://www.open-notebook.ai](https://www.open-
 
 ### Built With
 
-* [![Python][Python]][Python-url]
+[![Python][Python]][Python-url] [![SurrealDB][SurrealDB]][SurrealDB-url] [![LangChain][LangChain]][LangChain-url] [![Streamlit][Streamlit]][Streamlit-url]
-* [![SurrealDB][SurrealDB]][SurrealDB-url]
-* [![LangChain][LangChain]][LangChain-url]
-* [![Streamlit][Streamlit]][Streamlit-url]
 
 <p align="right">(<a href="#readme-top">back to top</a>)</p>
 
@@ -156,6 +153,10 @@ Go to the [Usage](docs/USAGE.md) page to learn how to use all features.
 
 ## 🚀 New Features
 
+### v0.0.9 - Ask your Documents and Citations  ❓
+
+- Ask questions about your documents and get answers with citations
+
 ### v0.0.7 - Model Management  🗂️
 
 - Manage your AI models and providers in a single interface

docs/PODCASTS.md

@@ -14,10 +14,17 @@ Setup a template for your podcast, you can get very creative here.
 - Pick a language for the podcast
 - Customize conversation style, engagement techniques, dialogue structure
 - Define the length of each episode
-- Pick your voice models (Open AI and Eleven Labs supported)
+- Pick your voice models (Open AI, Gemini and Eleven Labs supported)
 
 ![Podcast Temmplates](assets/podcast_template.png)
 
+### ⚠️ Important instructions for Gemini
+
+The new Gemini Text to Speech models are amazing and definitely worth using. But in order to use them, you need to do a little setup. Please refer to this [Podcastfy help page](https://github.com/souzatharsis/podcastfy/blob/main/usage/config.md) for details. But it basically requires you to enable the Text to Speech API and add it to your API Key.
+
+
+
+
 ### Pick your context
 
 Pick the specific context you'd like to use to base your podcast. 

open_notebook/models/__init__.py

@@ -24,6 +24,7 @@ from open_notebook.models.speech_to_text_models import (
 )
 from open_notebook.models.text_to_speech_models import (
     ElevenLabsTextToSpeechModel,
+    GeminiTextToSpeechModel,
     OpenAITextToSpeechModel,
     TextToSpeechModel,
 )
@@ -56,6 +57,7 @@ MODEL_CLASS_MAP: Dict[str, ProviderMap] = {
     "text_to_speech": {
         "openai": OpenAITextToSpeechModel,
         "elevenlabs": ElevenLabsTextToSpeechModel,
+        "gemini": GeminiTextToSpeechModel,
     },
 }
 

open_notebook/models/text_to_speech_models.py

@@ -24,3 +24,8 @@ class OpenAITextToSpeechModel(TextToSpeechModel):
 @dataclass
 class ElevenLabsTextToSpeechModel(TextToSpeechModel):
     model_name: str
+
+
+@dataclass
+class GeminiTextToSpeechModel(TextToSpeechModel):
+    model_name: str

pages/5_🎙️_Podcasts.py

@@ -97,6 +97,10 @@ with templates_tab:
         st.markdown(
             "[Open AI voices](https://platform.openai.com/docs/guides/text-to-speech)"
         )
+        st.markdown(
+            "[Gemini voices](https://cloud.google.com/text-to-speech/docs/voices)"
+        )
+
         pd_cfg["voice2"] = st.text_input(
             "Voice 2", help="You can use Elevenlabs voice ID"
         )
@@ -211,6 +215,9 @@ with templates_tab:
             st.markdown(
                 "[Open AI voices](https://platform.openai.com/docs/guides/text-to-speech)"
             )
+            st.markdown(
+                "[Gemini voices](https://cloud.google.com/text-to-speech/docs/voices)"
+            )
             pd_config.voice2 = st.text_input(
                 "Voice 2",
                 value=pd_config.voice2,

pages/7_⚙️_Settings.py

@@ -77,9 +77,13 @@ with model_tab:
             available_model_types,
             help="Use language for text generation models, text_to_speech for TTS models for generating podcasts, etc.",
         )
-        model_name = st.text_input(
+        if model_type == "text_to_speech" and provider == "gemini":
-            "Model Name", "", help="gpt-4o-mini, claude, gemini, llama3, etc"
+            model_name = "gemini-default"
-        )
+            st.markdown("Gemini models are pre-configured. Using the default model.")
+        else:
+            model_name = st.text_input(
+                "Model Name", "", help="gpt-4o-mini, claude, gemini, llama3, etc"
+            )
         if st.button("Save"):
             model = Model(name=model_name, provider=provider, type=model_type)
             model.save()

pages/stream_app/chat.py

@@ -88,14 +88,17 @@ def chat_sidebar(current_notebook: Notebook, current_session: ChatSession):
                         "No notes or sources found in context. You don't want a boring podcast, right? So, add some context first."
                     )
                 else:
-                    if st.button("Generate"):
+                    try:
-                        with st.spinner("Go grab a coffee, almost there..."):
+                        if st.button("Generate"):
-                            selected_template.generate_episode(
+                            with st.spinner("Go grab a coffee, almost there..."):
-                                episode_name=episode_name,
+                                selected_template.generate_episode(
-                                text=context,
+                                    episode_name=episode_name,
-                                instructions=instructions,
+                                    text=context,
-                            )
+                                    instructions=instructions,
-                        st.success("Episode generated successfully")
+                                )
+                            st.success("Episode generated successfully")
+                    except Exception as e:
+                        st.error(f"Error generating episode - {str(e)}")
             st.page_link("pages/5_🎙️_Podcasts.py", label="🎙️ Go to Podcasts")
     with chat_tab:
         with st.expander(

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "open-notebook"
-version = "0.0.9"
+version = "0.0.10"
 description = "An open source implementation of a research assistant, inspired by Google Notebook LM"
 authors = ["Luis Novo <lfnovo@gmail.com>"]
 license = "MIT"
@@ -40,7 +40,7 @@ langchain-ollama = "^0.2.0"
 langchain-google-vertexai = "^2.0.5"
 sdblpy = "^0.3.0"
 langchain-google-genai = "^2.0.1"
-podcastfy = "^0.2.8"
+podcastfy = "^0.3.2"
 tomli = "^2.0.2"
 bs4 = "^0.0.2"
 python-docx = "^1.1.2"