May 22, 2026
🌍 Simulation Language Support, Node.js LiveKit SDK & Pipecat v1
Simulation Language & Accent Support — The simulation environment now supports a wider range of languages and regional accents, so you can test your agent across diverse user demographics without changing your evaluation setup. Supported languages include English (US, UK, Australian), Arabic (Egyptian, UAE, Saudi Arabian), French (France, Canadian), Spanish (Spain, Mexican), German (Germany, Austrian, Swiss), and Italian. Node.js LiveKit SDK — Thetuner-livekit-sdk is now available for Node.js. Connect your LiveKit agents to Tuner in two lines of code — session data including transcripts, usage, latency, and cost is captured and pushed to Tuner automatically when each session ends. Learn more →
Pipecat v1 Support — The tuner-pipecat-sdk has been updated to support Pipecat v1, keeping your monitoring pipeline compatible with the latest Pipecat release. Learn more →
Dograh Integration — Connect your Dograh voice workflow to Tuner in minutes. Add the Tuner node to your workflow, create a Dograh agent in Tuner, and paste in your credentials — completed calls are exported automatically for analysis, evaluation, and monitoring. Learn more →
May 15, 2026
🤖 Simulation
Simulation — Test your voice agent against a realistic simulated user before shipping to production. Tuner automatically generates caller scenarios based on your agent’s configuration — no manual setup required. Each simulated call is evaluated against your configured evals and outcomes, so you can catch regressions, validate prompt changes, and stress-test edge cases without involving real users. Key Features:- Auto-generated scenarios — Tuner generates caller scenarios from your agent configuration and use case selections, so simulations are always grounded in your agent’s actual context
- Functional & pressure testing — Control the mix between functional tests that validate core use cases and adversarial pressure tests that probe failure modes and edge cases
- Targeted runs — Run simulations against a specific use case or a specific eval to isolate and validate exactly what you’re working on
- Automated evaluation — Each simulated call is scored against your existing evals, outcomes, and red flags
April 2, 2026
😊 Auto Sentiment Detection
Auto Sentiment Detection — Sentiment is now automatically detected and added as a default metric for every call — no configuration required. Tuner analyzes the conversation to surface caller sentiment signals, giving you an immediate read on call quality and user experience trends across your full call volume.March 23, 2026
📊 Enhanced Voice Metrics, Vapi Integration & Webhook Support
Enhanced Voice Metrics — The voice metrics dashboard now includes a detailed breakdown of latency by component — STT, TTS, and LLM — so you can pinpoint exactly where delays are introduced in your pipeline. Metrics are reported at the p50 and p90 percentiles, giving you a clearer picture of both typical performance and tail latency across your call volume. Vapi Integration — Connect your Vapi agents to Tuner with native platform support. Call data — transcripts, latency, evaluations, and cost — is captured and pushed to Tuner automatically for every Vapi-powered session. Learn more → Webhook Support for Retell & Vapi — You can now register additional webhooks in Tuner alongside your existing Retell and Vapi configuration. Tuner now forwards call payloads to your webhook URL after processing, so your existing automations keep running alongside Tuner without any changes.Learn more →March 19, 2026
🔌 LiveKit & Pipecat SDKs, and Transcript Improvements
LiveKit SDK — Connect your LiveKit Agents to Tuner in two lines of code. Thetuner-livekit-sdk automatically captures session data — transcripts, usage, latency, and cost — and pushes it to Tuner when each session ends. No manual API calls required. Learn more →
Pipecat SDK — Monitor your Pipecat Flows pipelines with the new tuner-pipecat-sdk. The FlowsObserver captures flow transitions, latency signals, transcripts, and usage metadata, then sends a structured call payload to Tuner when the call ends. Learn more →
⚙️ Agents API — Create, retrieve, and update your agents programmatically via API. Learn more →
📋 Transcript Function Call View — Tool calls now appear inline in the transcript with their input arguments and output responses, making it easier to debug unexpected agent behavior.
March 10, 2026
🔗 Metadata-Linked Evals & MCP Improvements
Metadata-Linked Evals — Evals can now reference call metadata, so they stay accurate even when agent instructions change per session or tenant. Attach any runtime context when pushing calls (instructions, tenant config, session properties) and each call is evaluated against its own context, not a shared static policy. Learn more → Tuner MCP Improvements — Enhanced the MCP prompt with deeper understanding of your agent’s context. It now suggests more comprehensive configuration across outcomes, intents, evals, red flags, and data extraction, plus ships with richer built-in templates so your initial setup is closer to production-ready out of the box.February 25, 2026
⚡ Tuner MCP
Manage your agent’s observability configuration directly from your IDE or AI assistant using natural language. Tuner MCP lets you connect Tuner to tools like Cursor, Claude, Claude Code, and Antigravity — so you can manage your tuner agent without leaving your workflow. Key Features:- Set up observability for a new agent in minutes using natural language setup
- IDE Integration — configure Tuner from your development environment with API-key authentication
- Chat-Based Management — connect via OAuth and manage your agent through conversational prompts
- Iterate on your agent evaluations without leaving your workflow
February 18, 2026
📝 Call Log Transcript View
View the full conversation transcript directly from the Call Log details page — with speaker labels and timestamps. Use Cases:- Review exactly what was said during a flagged or failed call
- Verify agent responses against expected behavior
- Share transcript excerpts with your team for coaching or debugging
February 13, 2026
🔔 Real-Time Alerts
Get notified via Email when red flags, evaluation failures, or specific conditions are detected in your calls. Key Features:- Red Flag & Evaluation Triggers — fire alerts on hallucination, dead air, failed evals, and more
- Configurable Conditions — set thresholds and filters to control when alerts are sent
February 9, 2026
🚨 Red Flags & Issue Triage
Automatically detect critical issues across your calls — Hallucination, Early Hangup, Dead Air, Intent Missed, and High Latency. Use Cases:- Triage the most critical issues first by filtering calls by red flag type
- Track red flag frequency over time to measure the impact of changes
- Investigate root causes by reviewing flagged transcripts alongside agent settings
February 5, 2026
📊 Performance & Behavior Dashboards
Two purpose-built dashboards for full visibility into your agent — from high-level trends to granular behavior analysis. Key Features:- Performance Analysis — track call volume, success rates, and key metrics over time
- Behavior Analysis — surface pass/fail rates for evals and spot recurring red flags
- Time-Range Filters & Agent Drill-Down — isolate data by date range or specific agent
February 3, 2026
🔌 Public API & Custom Integration
Send call data from any voice platform to Tuner with a singlePOST request — no pre-built integration required.
Key Features:
- Single-Endpoint API — one request to push transcripts, metadata, and properties
- Platform Agnostic — works with any voice platform or custom-built system
- User Sentiment Support — include caller sentiment for richer analysis
February 1, 2026
🎉 Tuner Launch
Tuner is live — the observability and monitoring platform built for voice AI agents. Full visibility into every call your agent handles. Key Features:- End-to-End Call Monitoring — every call is captured, transcribed, and analyzed automatically
- Configurable Evaluations — define call outcomes, user intents, and evals tailored to your agent
- Native Integrations — connect directly to Retell, VAPI, Bland, and more with one-click setup
- Credit-Based Pricing — pay only for what you use, with a free tier to get started