Release notes

Telnyx Voice AI Assistants now support Anthropic Claude Haiku 4.5 as a native model option. Developers can deploy the model without managing Anthropic API keys, while still retaining the option to bring their own credentials.

Telnyx has deployed GPUs in Sydney, enabling ultra-low-latency, onshore Voice AI Agents that deliver natural, human-like conversations for Australian businesses.

Telnyx Voice AI Agents now support warm transfers, allowing real-time handoffs between agents with conversation context included to avoid repeated information and improve call flow efficiency.

Telnyx now supports GPT-5 and Groq gpt-oss-120b for Voice AI Agents, delivering more choice, faster responses, and cost-efficient performance for real-time voice.

The Telnyx TypeScript/React Library gives developers full control to build custom Voice AI Agent widgets with low-latency, multimodal support.

Telnyx Voice AI Agents now support receiving MMS messages during live calls. Users can send images mid-conversation, and the agent will interpret and respond instantly using a vision-enabled model like GPT-4o or LLaMA 4 Maverick.

Telnyx AI Agents now support built-in versioning and canary deployments, making it easy to experiment, test updates in production, and roll out changes safely.

Telnyx AI Agents now support native integration with MCP servers, making it easier than ever to connect with public APIs and automation tools like Zapier. Streamline development and expand your agent’s capabilities with minimal setup.

Telnyx AI Agents now come with built-in noise suppression that filters out background distractions automatically. This update delivers clearer, more natural voice interactions without any extra setup.

Telnyx just launched structured testing for AI Agents. Teams can now create natural-language test scenarios, define input variables, simulate conversations, and validate behavior before pushing changes to production all in one dedicated testing environment.

Telnyx has enhanced the AI Agent Handoff tool with support for both unified and distinct voice modes. Now, businesses can deliver either seamless, single-voice conversations or a dynamic “AI team” experience where each assistant keeps its own voice, giving you more flexibility to design natural, personalized customer interactions.