# Calibrate

## Docs

- [Overview](https://penseapp.vercel.app/docs/cli/overview.md): Command-line interface for evaluating voice agents
- [Simulations](https://penseapp.vercel.app/docs/cli/simulations.md): Run simulated conversations to test your agent end-to-end
- [Speech to Text](https://penseapp.vercel.app/docs/cli/speech-to-text.md): Evaluate Speech to Text providers via CLI
- [Text to Speech](https://penseapp.vercel.app/docs/cli/text-to-speech.md): Evaluate Text to Speech providers via CLI
- [LLM tests](https://penseapp.vercel.app/docs/cli/text-to-text.md): Create edge cases to test the LLM powering your agent
- [Agent Connections](https://penseapp.vercel.app/docs/core-concepts/agent-connections.md): Connect your existing deployed agent to Calibrate
- [Agents](https://penseapp.vercel.app/docs/core-concepts/agents.md): Create AI agents to evaluate and improve
- [Metrics](https://penseapp.vercel.app/docs/core-concepts/metrics.md): Define how to evaluate agent performance in simulations
- [Personas](https://penseapp.vercel.app/docs/core-concepts/personas.md): Create realistic personas matching your target audience
- [Scenarios](https://penseapp.vercel.app/docs/core-concepts/scenarios.md): Define what your simulated users should do in simulations
- [Speech to Text](https://penseapp.vercel.app/docs/core-concepts/speech-to-text.md): Understand the concepts for evaluating Speech To Text providers
- [Text to Speech](https://penseapp.vercel.app/docs/core-concepts/text-to-speech.md): Understand the concepts for evaluating Text to Speech providers
- [Tools](https://penseapp.vercel.app/docs/core-concepts/tools.md): Learn how to create tools for your agents
- [Use cases](https://penseapp.vercel.app/docs/examples/overview.md): Examples of using Calibrate to improve AI agents
- [Introduction](https://penseapp.vercel.app/docs/getting-started/introduction.md): Learn about Calibrate and how to get started.
- [Configuring Tools](https://penseapp.vercel.app/docs/guides/configuring-tools.md): Define the tools for LLM evaluations and simulations via CLI
- [LLM](https://penseapp.vercel.app/docs/integrations/llm.md): Supported LLM providers in Calibrate
- [Speech to Text](https://penseapp.vercel.app/docs/integrations/stt.md): Supported STT providers in Calibrate
- [Text to Speech](https://penseapp.vercel.app/docs/integrations/tts.md): Supported TTS providers in Calibrate
- [Simulations](https://penseapp.vercel.app/docs/quickstart/simulations.md): Run simulated conversations with your agents
- [Speech to Text](https://penseapp.vercel.app/docs/quickstart/speech-to-text.md): Learn how to evaluate and compare STT providers with your data
- [Text to Speech](https://penseapp.vercel.app/docs/quickstart/text-to-speech.md): Learn how to evaluate and compare TTS providers with your data
- [LLM tests](https://penseapp.vercel.app/docs/quickstart/text-to-text.md): Create edge cases to test the LLM powering your agent

## OpenAPI Specs

- [openapi](https://penseapp.vercel.app/docs/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/artpark-sahai-org/calibrate)
- [WhatsApp](https://chat.whatsapp.com/JygDNcZ943a3VmZDXYMg5Z)