# Speaker Diarization Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/speaker-diarization
> Markdown URL: https://aitinkerers.org/technologies/speaker-diarization.md
> Technology record last updated: 2026-03-05T10:28:17Z
> Generated: 2026-09-22T21:35:46Z

Speaker Diarization automatically partitions an audio stream, leveraging AI to identify and label who spoke when in multi-speaker recordings.

This AI-driven process segments an audio file, performing two core functions: Speaker Detection (identifying the total number of unique voices) and Speaker Attribution (assigning each speech segment to a specific label, e.g., Speaker 1, Speaker 2). The system analyzes voice characteristics (pitch, tone) to create speaker embeddings, clustering them for high-accuracy labeling. This capability is critical for enhancing Automatic Speech Recognition (ASR) readability, transforming raw meeting transcripts and call center analytics into actionable, speaker-attributed data.

- Official technology site: https://www.assemblyai.com/blog/what-is-speaker-diarization/
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [MixedVoices: Tracking and Improving Voice Agents](https://bengaluru.aitinkerers.org/talks/rsvp_VH5ioEeVmJ4)

MixedVoices is an open source analytics and testing platform for voice agents. It helps builders track, visualize, and optimize performance by view conversation flowcharts, running simulations and suggesting prompt improvements. Technical Details: - LLM chain of thought to break calls into reusable and deterministic steps - Diarization of audio: Still not solved, accuracy of current solutions is still subpar, using stereo audio instead - Emotion analysis: gpt4o (hume planned later) - Using flowcharts to condense 1000s of recordings and create simulations that cover all edge cases - Creating simulations to test agent on, ensuring entire graph is covered Demo Structure: - My experience in building Voice agents and facing problems due to unreliability - Project walk through: Python API (Few lines of code to integrate) + Streamlit Dashboard (Runs locally) - Importance of Version control to track agent evolution over time - Examples of edge cases discovered - Examples of simulations and how they help in continuous evaluation

- Event context: AI Tinkerers Bengaluru - December - RSVP REQUIRED — 2024-12-05 — Bengaluru
- Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_VH5ioEeVmJ4

### [Creation of transcription engine for capsule.video](https://la.aitinkerers.org/talks/rsvp_xUP--SS3F7U)

I'll share the details of how Capsule Transcriber works and demonstrate the full-stack analytics app that I've built to compare and validate various transcription models and APIs. Capsule Transcriber consists of 5 ML models, and you will learn about Voice Activity Detection, Whisper, Speaker Diarization, Timestamps, Language Detection, etc.

- Event context: March 19th - LA AI Tinkerers Meetup & Demos — 2024-03-20 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_xUP--SS3F7U

## Related Technologies

- [Emotion Analysis](https://aitinkerers.org/technologies/emotion-analysis) ([Markdown](https://aitinkerers.org/technologies/emotion-analysis.md)) — 1 public demo
- [GPT-4o](https://aitinkerers.org/technologies/gpt-4o) ([Markdown](https://aitinkerers.org/technologies/gpt-4o.md)) — 57 public demos
- [Language Detection](https://aitinkerers.org/technologies/language-detection) ([Markdown](https://aitinkerers.org/technologies/language-detection.md)) — 1 public demo
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Streamlit](https://aitinkerers.org/technologies/streamlit) ([Markdown](https://aitinkerers.org/technologies/streamlit.md)) — 89 public demos
- [Timestamps](https://aitinkerers.org/technologies/timestamps) ([Markdown](https://aitinkerers.org/technologies/timestamps.md)) — 1 public demo
- [WebRTC-VAD](https://aitinkerers.org/technologies/webrtc-vad) ([Markdown](https://aitinkerers.org/technologies/webrtc-vad.md)) — 2 public demos
- [Whisper](https://aitinkerers.org/technologies/whisper) ([Markdown](https://aitinkerers.org/technologies/whisper.md)) — 26 public demos