Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Instantcasts: Fast Whisper Transcripts
Learn how to process an hour‑long podcast in under ten seconds using optimized Whisper inference, covering model tweaks, audio storage, chunking, prompting, and diarization.
I’ve been working on a fun side project around fast Whisper inference that takes the URL to a podcast and, in <10 seconds for an hour-long show, generates a transcript and summary. The actual application is super basic, but it showcases some advanced stuff around optimizing Whisper inference at both a model level and an infra level (e.g. where does the podcast audio file live? it matters!)
- WhisperWhisper: OpenAI's robust, open-source ASR model for multilingual speech recognition, translation, and language identification.Whisper is OpenAI's general-purpose Automatic Speech Recognition (ASR) model, trained on a massive, diverse dataset for high-accuracy performance. It functions as a powerful multitasking system: handling multilingual transcription, direct speech translation, and language identification. The architecture processes audio in a sliding 30-second window, performing autoregressive predictions. Developers can select from six distinct model sizes to optimize for specific speed versus accuracy tradeoffs: this is the go-to solution for reliable, large-scale audio processing.
Related projects
Daily AI generated pep talks
New York City
This talk demonstrates a no/low code automation that uses APIs and voice synthesis to deliver personalized daily pep…
AI Call Analyst
Medellín
Learn how to convert recruiter‑candidate call audio to text, assess pronunciation, apply business criteria with an LLM, score…
AI Generated Podcasts
Phoenix
Demo of a tool that converts newsletter and blog text into podcasts, showing practical applications for employee training…
Automated Podcast Research & Creation Studio
Los Angeles
This talk demonstrates how to create and automate recurring podcasts using AI hosts, real-time data integration, REST APIs,…
Building blocks for voice-to-voice AI
San Francisco
This talk demonstrates building fast, reliable voice-to-voice AI bots using open source tools, covering key components and showing…
podscript - CLI tool to generate podcast transcripts using language and speech-to-text models
Bengaluru
Learn how podscript uses LLMs and speech‑to‑text APIs like ChatGPT, Anthropic, Deepgram, and Groq to generate accurate podcast…