Sign in

Samrat Man Singh

@samrat.me
950 followers 171 following 94 posts

Software engineer; climber; #ElixirLang Website: samrat.me Building octocut.com

PostsRepliesMedia
Samrat Man Singh @samrat.me · 19/08/2025
lu.ma/33ghwjqt
lu.ma
Ship It Club Berlin · Luma
Ship It Club Berlin: Kickoff Meetup The very first ShipIt Club meetup is here! Join a growing community of mobile devs, indie hackers, and app founders who are…
000
Samrat Man Singh @samrat.me · 19/08/2025
Attending this later today. Anyone else I know going?
100
Samrat Man Singh @samrat.me · 12/06/2025
2/ @maciej.gryka.net walked us through an Elixir version of @thorstenball.com 's coding agent tutorial
031
Samrat Man Singh @samrat.me · 12/06/2025
Great presentations and conversation at the Elixir Berlin Meetup today 1/ Lukas talked about his big bag of Postgres tricks and techniques #elixirlang
230
Samrat Man Singh @samrat.me · 12/06/2025
No, haven't tried it yet. I like the simple Python interface though. Should be simple to get the audio to Elixir using Pythonx, I think 🤔
010
Samrat Man Singh @samrat.me · 06/06/2025
I found Pantheon from your earlier post, and really enjoyed it. Appreciate the book and show reviews/recommendations!
120
Samrat Man Singh @samrat.me · 14/05/2025
github.com/samrat/membr...
github.com
GitHub - samrat/membrane_twilio_plugin
Contribute to samrat/membrane_twilio_plugin development by creating an account on GitHub.
020
Reposted by Samrat Man Singh
Paulo Valente @polvalente.social · 11/05/2025
I've just released Handoff, a new Elixir library for distributed function graph execution. hexdocs.pm/handoff Among other things, the library enables distributed Nx computations (anyone said distributed inference?) A huge part of this was sponsored by tvlabs.ai!
hexdocs.pm
Handoff v0.1.0 — Documentation
25715
Reposted by Samrat Man Singh
José Valim @josevalim.bsky.social · 29/04/2025
Introducing Tidewave: tidewave.ai While working on our web apps, we run code, query the database, read logs, search docs… but our AI tools are limited to reading code. Tidewave closes this gap by introducing Runtime Intelligence, for Phoenix and Rails. More coming soon, check out the website!
tidewave.ai
Tidewave
517760
Samrat Man Singh @samrat.me · 02/04/2025
Gemini has a slightly different schema for tool declarations: github.com/thmsmlr/inst...
github.com
instructor_ex/lib/instructor/adapters/gemini.ex at 2c89b1cd52e0125562c8c5cb2eb99d2324261cfa · thmsmlr/instructor_ex
Structured outputs for LLMs in Elixir. Contribute to thmsmlr/instructor_ex development by creating an account on GitHub.
110
Samrat Man Singh @samrat.me · 27/03/2025
Demo: Making phone calls from Elixir I'm working on a Twilio plugin for the Membrane multimedia framework. The demo shows an outbound call, but receiving calls works too. #ElixirLang www.youtube.com/watch?v=4dhl...
youtube.com
Making phone calls from Elixir using Twilio
YouTube video by Samrat Man Singh
3100
Samrat Man Singh @samrat.me · 26/03/2025
Are you using AI studio? Are you using any tools to feed multiple files to it?
100
Samrat Man Singh @samrat.me · 26/03/2025
Testing Voice AI flows can become tedious fast But... you can just simulate conversations using another voice agent. Then, evaluate how the conversation went.
020
Samrat Man Singh @samrat.me · 21/03/2025
Got a small, standalone Python script working to use the new OpenAI transcription models(`gpt-4o-transcribe` and `gpt-4o-mini-transcribe`) using the Realtime WebSocket connection: samrat.me/standalone-o...
samrat.me
Standalone OpenAI transcription Python script
OpenAI announced some new audio models yesterday, including new transcription models(gpt-4o-transcribe and gpt-4o-mini-transcribe). This model performs better than Whisper, though because they are bui...
001
Samrat Man Singh @samrat.me · 20/03/2025
www.openai.fm
openai.fm
OpenAI.fm
An interactive demo for developers to try the new text-to-speech model in the OpenAI API
000
Samrat Man Singh @samrat.me · 20/03/2025
OpenAI's new TTS looks(and sounds) pretty great for the price. Also, I hope this pushes other providers to just price API usage by minute. Every other TTS provider(ElevenLabs, Cartesia, etc) currently have monthly credits pricing.
110
Samrat Man Singh @samrat.me · 20/03/2025
Phoenix now comes with DaisyUI. Looks like a great addition for non-designers(like me) #ElixirLang
43510
Samrat Man Singh @samrat.me · 20/03/2025
Got it, thank you!
000
Samrat Man Singh @samrat.me · 19/03/2025
What would be the reason to switch to Canadian/EU-based institutions? 🤔
100
Samrat Man Singh @samrat.me · 09/03/2025
There's a video here if you still have a Twitter account x.com/thmsmlr/stat...
x.com
Thomas Millar on X: "✨ Introducing Livebook Tools ✨ BYOE(ditor) — Cursor and Windsurf now work with Livebook Livebook MCP Server — Claude can fetch the outputs of a running livebook to see what to do next `livebook_tools run notebook.livemd` — Run .livemd from the CLI. Livebook 🤝 CRON https://t.co/d7jSesgtyj" / X
✨ Introducing Livebook Tools ✨ BYOE(ditor) — Cursor and Windsurf now work with Livebook Livebook MCP Server — Claude can fetch the outputs of a running livebook to see what to do next `livebook_tools run notebook.livemd` — Run .livemd from the CLI. Livebook 🤝 CRON https://t.co/d7jSesgtyj
030
Samrat Man Singh @samrat.me · 09/03/2025
New #ElixirLang tool LivebookTools lets you work on Livebook in your own editor and opens MCP access to cell outputs(so Cursor, etc) can automatically iterate on the code if the cell has errors github.com/thmsmlr/live...
github.com
GitHub - thmsmlr/livebook_tools: Powertools for livebook.dev — AI Code Editing, MCP Servers, and Running Livebooks from the CLI
Powertools for livebook.dev — AI Code Editing, MCP Servers, and Running Livebooks from the CLI - thmsmlr/livebook_tools
1112
Samrat Man Singh @samrat.me · 04/03/2025
:D Merged. Thanks Lars!
010
Reposted by Samrat Man Singh
Lars Wikman @lawik.bsky.social · 04/03/2025
What does talk-prep look like? Bug-fixin' mostly @samrat.me darling, you have a PR :D github.com/samrat/kokor...
github.com
Fix concatenation issue for tensors by lawik · Pull Request #5 · samrat/kokoro
Nx.concatenate requires the same shape and very frequently a random chunk of text would not be the right shape. So it would blow up. The concatenate was avoidable so instead of a complex padding sc...
111
Samrat Man Singh @samrat.me · 04/03/2025
Pushed my first @replicate.com model, SmolVLM2 by @hf.co (@pcuenq.hf.co et al.) Will push the 500M and 2.2B models soon as well.
040
Samrat Man Singh @samrat.me · 01/03/2025
Voice models are getting scary good. This one feels very human: www.sesame.com/research/cro...
sesame.com
Crossing the uncanny valley of conversational voice
At Sesame, our goal is to achieve “voice presence”—the magical quality that makes spoken interactions feel real, understood, and valued.
010
Samrat Man Singh @samrat.me · 20/02/2025
I wrote up a post on how you can run AI models on Elixir that aren't yet supported by Bumblebee samrat.me/running-ml-m... #MyElixirStatus #ElixirLang
samrat.me
Running ML models in Elixir using Pythonx
I just discovered Pythonx, which runs a Python interpreter in the same OS process as Elixir. Looks like it also wraps uv so it sets up a virtual environment with all the Python dependencies your code...
1225
Samrat Man Singh @samrat.me · 20/02/2025
Wow, this looks super useful for running models that aren't yet supported in Bumblebee(among other things) #ElixirLang github.com/livebook-dev...
github.com
GitHub - livebook-dev/pythonx: Python interpreter embedded in Elixir
Python interpreter embedded in Elixir. Contribute to livebook-dev/pythonx development by creating an account on GitHub.
072
Samrat Man Singh @samrat.me · 14/02/2025
👀 Interesting! Are you using Membrane on embedded devices?
120
Reposted by Samrat Man Singh
David Bernheisel @david.bernheisel.com · 07/02/2025
Holy smokes this is awesome, a new debugger for Phoenix LiveView. Think React devtools, but not a chrome extension. github.com/software-man... #ElixirLang
515040
Reposted by Samrat Man Singh
Xenova @xenova.bsky.social · 07/02/2025
We did it! Kokoro TTS (v1.0) can now run 100% locally in your browser w/ WebGPU acceleration. Real-time text-to-speech without a server. ⚡️ Generate 10 seconds of speech in ~1 second for $0. What will you build? 🔥
1236
Reposted by Samrat Man Singh
Samrat Man Singh @samrat.me · 05/02/2025
Interested in how to build voice AI apps in Elixir? Here's a blog post I wrote about building a Membrane pipeline that orchestrates audio/video communication between a browser and Google Gemini #ElixirLang blog.swmansion.com/building-a-m...
blog.swmansion.com
Building a Membrane Pipeline to Talk to Google Gemini
Elixir, together with the Membrane framework, is great for building pipelines that enable seamless communication between users and LLMs.
171
Samrat Man Singh @samrat.me · 05/02/2025
Thanks to @swmansion.com for publishing the post. Their team also build and maintain the incredible Membrane framework.
100
Samrat Man Singh @samrat.me · 05/02/2025
And here's the Livebook github.com/samrat/gemin...
github.com
GitHub - samrat/gemini_live_with_membrane
Contribute to samrat/gemini_live_with_membrane development by creating an account on GitHub.
100
Samrat Man Singh @samrat.me · 05/02/2025
Interested in how to build voice AI apps in Elixir? Here's a blog post I wrote about building a Membrane pipeline that orchestrates audio/video communication between a browser and Google Gemini #ElixirLang blog.swmansion.com/building-a-m...
blog.swmansion.com
Building a Membrane Pipeline to Talk to Google Gemini
Elixir, together with the Membrane framework, is great for building pipelines that enable seamless communication between users and LLMs.
171
Samrat Man Singh @samrat.me · 04/02/2025
Awesome, will check it out. I'm also preparing a Livebook to do something similar(using a Kino form instead of stdin): bsky.app/profile/did:...
100
Reposted by Samrat Man Singh
Lars Wikman @lawik.bsky.social · 04/02/2025
Had some fun generating speech using the Elixir Kokoro implementation by @samrat.me. Made a script for typing stuff and getting the talky-talk. github.com/samrat/kokor... So a bit of ONNX, some Erlang Ports, Membrane :D #elixirlang
github.com
Mix.install-based example beyond raw audio · Issue #4 · samrat/kokoro
This will start prompting your terminal for input and speak it to your default audio output. I have this other example unrelated to TTS that includes working with files and MP3s. #!/usr/bin/env eli...
1103
Samrat Man Singh @samrat.me · 31/01/2025
Reworking the Livebook for Kokoro(🔊 text-to-speech model). Now, you get a text input to input text you want read out loud(or whispered) to you. #MyElixirStatus #ElixirLang
093
Samrat Man Singh @samrat.me · 26/01/2025
Writing up a blog post about this. Not sure how much of it should be an introduction to Membrane. #ElixirLang
051
Samrat Man Singh @samrat.me · 25/01/2025
It should be possible to do it using Elixir, but I imagine it would be full of edge-cases, especially if you start looking into multiple languages.
130
Samrat Man Singh @samrat.me · 25/01/2025
I was also surprised that the text-to-phonemes step happens outside the model. Larger TTS models do seem to do work end-to-end(text input instead of phonemes as input): huggingface.co/hexgrad/Koko...
huggingface.co
hexgrad/Kokoro-82M · Curb Your Expectations: Data & Architecture Limitations
Two things you should be aware of
020
Samrat Man Singh @samrat.me · 25/01/2025
Elixir bindings for Kokoro TTS github.com/samrat/kokoro #ElixirLang
github.com
GitHub - samrat/kokoro: Elixir bindings to Kokoro-82M text-to-speech model
Elixir bindings to Kokoro-82M text-to-speech model - samrat/kokoro
191
Samrat Man Singh @samrat.me · 25/01/2025
Here you go: github.com/samrat/kokoro Let me know if you run into issues running it.
github.com
GitHub - samrat/kokoro: Elixir bindings to Kokoro-82M text-to-speech model
Elixir bindings to Kokoro-82M text-to-speech model - samrat/kokoro
120
Samrat Man Singh @samrat.me · 09/01/2025
Have you tested this with the `4o-mini` model? It's cheaper, but in my experience it becomes much less reliable at function calling. Curious if that's a general issue, or just skill issue on my part.
100
Samrat Man Singh @samrat.me · 07/01/2025
Oops, forgot to tag #ElixirLang
050
Samrat Man Singh @samrat.me · 07/01/2025
More voice AI exploration: Bumblebee doesn't currently support text-to-speech models, but managed to get Kokoro TTS working with Ortex Demo 👇 youtu.be/VFKX6Af9gs4
youtu.be
Elixir text-to-speech with Kokoro
YouTube video by Samrat Man Singh
1142
Reposted by Samrat Man Singh
antirez @antirez.bsky.social · 07/01/2025
Posted on HN. Feel like sharing here as well.
8536
Samrat Man Singh @samrat.me · 04/01/2025
I've been building a small voice AI app. So far, both OpenAI Realtime and Gemini Multimodal Live seem very unreliable with function calling. And Gemini insists that it did the function call😅
000
Samrat Man Singh @samrat.me · 30/12/2024
Got Gemini Multimodal Live API working with Membrane WebRTC. Here's me having a short chat with it #ElixirLang youtu.be/JxWE3pxyGqA
youtu.be
Talking to Gemini Multimodal Live with Membrane WebRTC
YouTube video by Samrat Man Singh
091
Samrat Man Singh @samrat.me · 29/12/2024
Boring title, but this is a delightful read on China, travel and life www.dwarkeshpatel.com/p/notes-on-c...
dwarkeshpatel.com
Notes on China
Last month, I spent 2 weeks in China - I visited Beijing, Chengdu, Emeishan, Chongqing, Shanghai, and Hangzhou.
000
Samrat Man Singh @samrat.me · 28/12/2024
What tool do you usually use for live clipping?
000