TalkThru

Technical interviews, presentations, salary negotiations, sharing bad news, thesis defenses … what do all these have in common? You need to practice. You need feedback. TalkThru is the professional you need for on-demand, face-to-face practice. Technical or behavioral, emotional or cold: test your speeches, knowledge & improvisation with immediate corrections. You provide a topic to the agent. You provide the agent a role. The agent holds a conversation with you and summarizes what you should improve on at the end. It’s that easy. 5 steps: Program initialization: User provides role & theme for the interview. Query: a) Share the prompt with Perplexity to generate an introduction, b) generate a fitting video with LumaLabs. ElevenLabs: translate Perplexity's text-based response to speech & begin the conversation. Speech2Text: The user's response to the agent's question is translated to text (using python speech_recognition). Re-query: Unless the user wants to end the conversation, repeat steps 2-4. Speech-to-text: pause identification, fast responses, storing & processing audio real-time were challenging aspects of the speech integration. Speech-to-text: pause identification, fast responses, storing & processing audio real-time were challenging aspects of the speech integration. Lip-syncing: realistic interview preparation requires mouth movement. Whereas LumaLabs provides vastly creative features, it does not support facial expressions. Our first feature release will enable lip syncing so that users can carry realistic conversations. Lip-syncing: realistic interview preparation requires mouth movement. Whereas LumaLabs provides vastly creative features, it does not support facial expressions. Our first feature release will enable lip syncing so that users can carry realistic conversations. CUDA integration: lip-syncing requires torch access, CUDA-based GPUs & many pre-trained models. Thanks to our sponsor NVIDIA, we were able to develop this feature. CUDA integration: lip-syncing requires torch access, CUDA-based GPUs & many pre-trained models. Thanks to our sponsor NVIDIA, we were able to develop this feature. Markdown & React.js fans try flask for the first time. GenAI is actually pretty fast. Run LLMs on CUDA! Run LLMs on CUDA! End-to-end integration of LLM queries for on-demand user requests. End-to-end integration of LLM queries for on-demand user requests. Successful project scoping Successful project scoping There is so much ground to cover: [Sun 2/16] Simultaneous conversations [Sun 2/23] Interview Summary & Grading [Sun 2/23] Interview Summary & Grading [Sun 2/23] Programming interviews [Sun 3/2] Design questions uploading Sketches & Block diagrams [Sun 3/9] User Assesment - free product campaign [Sun 3/16] Enhance sentimentality [ Difficult Conversations]