Moonshot AI released open weights for Kimi K3, made immediately available on Telnyx Inference API with emphasis on sovereign deployment on Telnyx-owned GPUs, according to Telnyx release notes. The mov…
Telnyx released a Python Flask example that redacts personally identifiable information (PII) from call transcripts and recordings using its AI inference API. The app replaces common PII types like na…
Telnyx has deployed the Kimi K3 model via its Inference API, offering an OpenAI-compatible endpoint that allows developers to switch from GPT-4o or Claude by changing only the base URL and model ID. T…
Kimi K3, a 2.8-trillion-parameter open-source AI model with a 1-million-token context window and native vision, is now available via Telnyx's OpenAI-compatible Inference API, enabling production teams…
Telnyx has added Moonshot AI's 2.8 trillion-parameter Kimi K3 model to its inference API, making the open-weights model available through an OpenAI-compatible interface. The model, which features a mi…
Telnyx has added Moonshot AI's Kimi K3, a 2.8-trillion-parameter open-source model, to its Inference API. The model, built on Kimi Delta Attention with a 1M-token context window and native vision capa…
A million words of AI output costs $50 from Anthropic's Fable and 87 cents from DeepSeek's V4-Pro, according to Fortune. Corporate America is shifting from tokenmaxxing to thrift-maxxing, substituting…
A developer built an Edge Fraud Firewall in 178 lines of Python that screens inbound calls at the carrier edge using Telnyx APIs and AI inference. The system classifies callers as CLEAN, SUSPICIOUS, o…
Telnyx has made OpenAI's GPT-5.4-mini available as an LLM model option for its Voice AI Assistants, allowing users to select the compact, high-efficiency model directly in assistant configuration with…
A developer built a Telnyx voice AI agent that automates pre-visit insurance clearance by turning patient phone calls into structured intake tickets. The agent uses Telnyx's Gather Using AI primitive …
A developer built a two-stage AI moderation classifier in Python using Telnyx AI Inference. The pipeline uses embeddings similarity to catch obvious spam and abuse patterns, then falls back to an LLM …
Telnyx has published a guide and open-source Go code demonstrating how to build a production backend for a voice AI assistant using a single Edge Compute function, handling both dynamic variables and …
NVIDIA Parakeet is now available as a speech-to-text engine for Telnyx Voice AI, enabling self-hosted multilingual transcription with automatic language detection for 25 European languages on Telnyx i…
Telnyx released a Go example demonstrating how to use a single Edge Compute function as the backend for an AI Assistant, handling dynamic variables and webhook tools without separate server infrastruc…
Telnyx released a Python example demonstrating a natural language to SQL API built with its AI Inference service. The Flask app accepts plain-English questions and returns generated SQL, explanations,…
Telnyx released a 104-line Python app called the AI Phone Story Hotline that lets callers dial a phone number, pick a genre, and hear an AI-generated interactive story that adapts to their choices in …
Telnyx released a one-curl audio translator built on its AI Inference API, combining STT, chat completions, and TTS in a single Flask app. The tool handles per-stage error handling, returning partial …
Telnyx released an open-source AI subscription cancel-save agent that classifies cancellation reasons, offers one relevant save option, and respects direct cancellation requests without manipulation. …
A developer built a hotel concierge line using Telnyx Voice, SMS, and Slack, combining Python Flask with Telnyx AI Inference to classify guest requests into categories like room service, housekeeping,…
Telnyx released a Python example that turns stack traces into structured debugging JSON using its AI Inference API. The Flask app accepts a stack trace and optional context, then returns a predictable…