CallMissed Blog
Insights on AI communication, voice agents, WhatsApp automation, and the future of customer engagement.
Sarvam Bulbul: TTS for Indian Voices and Code-Mixing
The hardest test of an Indian-language TTS model is not pronunciation — it's a sentence like "Aap apne SBI account ki KYC pending hai, please complete it before 25 तारीख." A name, an acronym, code-switched English, a Hindi date marker, and the whole thing has to sound like a real person reading a re…
Claude Mythos: Anthropic's Security-Focused Frontier
On April 7, 2026, Anthropic unveiled Claude Mythos Preview — a model the company described as "by far the most powerful AI model we've ever developed" — and immediately did something most labs don't: refused to release it publicly. Mythos is the most concrete public artifact yet of frontier AI being…
Why Model Context Protocol (MCP) Won the Agent Integration Wars
Eighteen months ago Model Context Protocol (MCP) was an Anthropic-released standard with a small reference implementation and a handful of integrations. As of March 2026, monthly SDK downloads passed 97 million, over 10,000 active public MCP servers exist, and 78% of enterprise AI teams report at le…
Nano Banana 2: How Gemini 3.1 Flash Image Beat the Field
On February 26, 2026, Google DeepMind launched Gemini 3.1 Flash Image, marketed under the "Nano Banana 2" codename, and within hours it took the #1 spot in the Artificial Analysis Image Arena — a blind human-evaluation leaderboard for text-to-image generation. The same release cut the API price in h…
On-Device AI in 2026: Apple Intelligence, Phi, and the Local LLM Renaissance
For most of LLMs' history, "local model" meant either "demo-quality" or "you own a GPU." In 2026 that has shifted. Small models tuned for consumer hardware are crossing the threshold of usefulness — not parity with frontier models, but good enough that real apps are shipping with on-device inference…
Inside GPT-5.5 Pro: OpenAI's Power-User Tier
GPT-5.5 Pro is the variant most users never touch — it costs roughly six times as much as standard GPT-5.5, requires a Pro/Business/Enterprise plan, and is reserved for the hardest single-shot tasks. But for the workloads that need it, nothing else in the OpenAI lineup is comparable. Here's where Pr…
GPT-Rosalind: OpenAI's Frontier Reasoning for Science
On April 16, 2026, OpenAI launched GPT-Rosalind, a frontier reasoning model built specifically for drug discovery, genomics, protein reasoning, and scientific research workflows. It's named for Rosalind Franklin, the British chemist whose X-ray crystallography work was central to discovering the str…
Anthropic-Compatible Messages API: Use Claude Without Vendor Lock-In
The Anthropic Messages API has its own design — a content-block model, system-prompt-as-top-level-field, native tool use, prompt caching, extended thinking. Apps built on Claude tend to use Anthropic's SDK directly, and migrating those apps usually means rewriting the call shape. CallMissed avoids t…
Building Voice Agents on CallMissed: From WebRTC to Sub-Second Round-Trip
A voice agent in 2026 is no longer a research demo. It is a real product surface — phone support, scheduling, in-app conversational UIs, embedded copilots — and the difference between one users tolerate and one users enjoy is almost entirely about latency and turn-taking. CallMissed gives you the pr…
How Llama 4's Mixture-of-Experts Architecture Works
Meta's Llama 4 family is the first Llama generation to ship as a Mixture-of-Experts (MoE) architecture. That single design choice explains most of what's different about Scout and Maverick — including why both have "17 billion active parameters" but very different total parameter counts, and why the…
The Complete 2026 Startup Credits Stack: Over $1M in Free Cloud, AI, and SaaS
If you are starting a company in 2026, the single biggest line item you can wipe off your runway is also the easiest one to apply for. Between cloud providers, AI labs, and SaaS vendors, a well-stacked startup can pull in well over $1M in free credits before paying for a single VM. Most founders lea…
Mistral Medium 3.5: One Model, Three Product Lines
Mistral released Medium 3.5 on April 29, 2026, and the most interesting thing about it isn't a benchmark number — it's the strategy. Where every other open-weight flagship in 2026 has gone Mixture-of-Experts, Mistral Medium 3.5 is dense, 128 billion parameters, with a 256K context window. And it con…
Qwen 3.5: Alibaba's Multilingual Powerhouse
Alibaba's Qwen line has quietly become the multilingual default for the open-weight world. The Qwen 3.5 release in February 2026 cemented that — the family now spans 201 languages and dialects, leads instruction-following benchmarks, and sets a new baseline for what an open-weight model can do acros…
Voice Agent Architecture in 2026: LiveKit, Pipecat, and the End of the Pipeline
For most of voice AI's history, the mental model was a pipeline: microphone → STT → LLM → TTS → speaker. Each stage was a discrete component, and the framework's job was to connect them. By 2026 that model is breaking down — partly because of multimodal models that fuse stages, partly because of arc…
Drop-In OpenAI-Compatible API: Switch Models Without Rewriting Your Code
The OpenAI Chat Completions API has won the LLM API design war. Whether you like the schema or not, every serious SDK and tool now speaks it natively — openai-python, openai-node, the LangChain/LlamaIndex adapters, the Anthropic CLI's compat mode, even some local model runners. CallMissed's /v1/chat…
Gemma 4: Google's Open-Weight Push for 2026
Google's Gemma line has always been the open-weight cousin to the closed-source Gemini family — same training pipeline, same research lineage, public weights, permissive license. Gemma 4 is the 2026 release, and the headline is that the 31B dense variant beats Llama 4 Scout on most reasoning benchma…
Multi-Tenant API Keys: Production-Grade Auth with cm_* Tokens
Most AI APIs treat keys as a binary: you have one, or you don't. That works for a hobby project. It does not work when you are deploying agents in production with separate environments, separate teams, separate budgets, and a security review in your future. CallMissed's cm API keys are designed for …
The Agentic AI Stack: From Tool Use to Autonomous Workflows
"Agent" was the most overused word in AI in 2024. By 2026 the term has stratified — a real agent stack now has identifiable layers, each with its own design decisions, failure modes, and competitive landscape. Here is how the stack looks today. Layer 1: The model This is the bottom of the stack and …
DeepSeek R2: The Open-Source Reasoning Surprise
DeepSeek's R2 is the model that made open-weight reasoning a real category in 2026. Reasoning models — the variants that explicitly think before answering — were a closed-vendor club through 2025. R2 changed that: a 32B-parameter open-weight checkpoint that runs on a single 24GB consumer GPU and cle…