# Voqal Docs

## Docs

- [Deepgram](https://docs.voqal.dev/compute/intent/deepgram.md): Deepgram is a speech recognition platform that uses deep learning to transcribe audio and video into text
- [Picovoice](https://docs.voqal.dev/compute/intent/picovoice.md): Picovoice is a platform for building voice products on the edge
- [Serenade](https://docs.voqal.dev/compute/intent/serenade.md): Open-source speech-to-code engine designed for developers
- [Anthropic](https://docs.voqal.dev/compute/llm/anthropic.md)
- [DeepSeek](https://docs.voqal.dev/compute/llm/deepseek.md)
- [Fireworks AI](https://docs.voqal.dev/compute/llm/fireworks.md)
- [Groq](https://docs.voqal.dev/compute/llm/groq.md)
- [Hugging Face](https://docs.voqal.dev/compute/llm/huggingface.md): Hugging Face is a company that provides a large collection of pre-trained models for natural language processing (NLP) tasks
- [Mistral AI](https://docs.voqal.dev/compute/llm/mistralai.md): Mistral AI is a platform that enables you to build, train, and deploy machine learning models at scale
- [Ollama](https://docs.voqal.dev/compute/llm/ollama.md): Get up and running with large language models, locally
- [OpenAI](https://docs.voqal.dev/compute/llm/openai.md): OpenAI TTS is a text-to-speech model that aims to provide high-quality and natural-sounding speech synthesis
- [Together AI](https://docs.voqal.dev/compute/llm/togetherai.md): Together AI is a platform that enables you to build and deploy AI models in a collaborative environment
- [Gemini](https://docs.voqal.dev/compute/mm/gemini.md): Google’s largest and most capable AI model
- [Helicone](https://docs.voqal.dev/compute/observability/helicone.md): Open-source LLM monitoring and analysis tool
- [Overview](https://docs.voqal.dev/compute/overview.md): Equip your Voqal Assistant with enhanced computational capabilities
- [AssemblyAI](https://docs.voqal.dev/compute/stt/assemblyai.md)
- [Deepgram](https://docs.voqal.dev/compute/stt/deepgram.md): Deepgram is a speech recognition platform that uses deep learning to transcribe audio and video into text
- [Groq (Whisper)](https://docs.voqal.dev/compute/stt/groq.md)
- [OpenAI](https://docs.voqal.dev/compute/stt/openai.md): OpenAI TTS is a text-to-speech model that aims to provide high-quality and natural-sounding speech synthesis
- [Picovoice](https://docs.voqal.dev/compute/stt/picovoice.md): Picovoice is a platform for building voice products on the edge
- [Deepgram](https://docs.voqal.dev/compute/tts/deepgram.md): Deepgram is a speech recognition platform that uses deep learning to transcribe audio and video into text
- [OpenAI](https://docs.voqal.dev/compute/tts/openai.md): OpenAI TTS is a text-to-speech model that aims to provide high-quality and natural-sounding speech synthesis
- [Picovoice](https://docs.voqal.dev/compute/tts/picovoice.md): Picovoice is a platform for building voice products on the edge
- [Picovoice](https://docs.voqal.dev/compute/vad/picovoice.md): Picovoice is a platform for building voice products on the edge
- [Voqal](https://docs.voqal.dev/compute/vad/voqal.md): Embedded voice activity detection (VAD) library
- [Add User Context](https://docs.voqal.dev/context/embedded/functions/add-user-context.md)
- [Chunk Text](https://docs.voqal.dev/context/embedded/functions/chunk-text.md)
- [Get User Context](https://docs.voqal.dev/context/embedded/functions/get-user-context.md)
- [Slurp URL](https://docs.voqal.dev/context/embedded/functions/slurp-url.md)
- [Assistant](https://docs.voqal.dev/context/embedded/variables/assistant.md)
- [Computer](https://docs.voqal.dev/context/embedded/variables/computer.md)
- [Examples](https://docs.voqal.dev/context/examples.md)
- [Overview](https://docs.voqal.dev/context/overview.md): Personalize your Voqal Assistant for your workflow, codebase, and team
- [Customization](https://docs.voqal.dev/customization.md): Your Voqal Assistant is adaptable and teachable
- [Changelog](https://docs.voqal.dev/development/changelog.md): Lists the changes between Voqal versions
- [Introduction](https://docs.voqal.dev/introduction.md): Voqal — Voice native AI agent for the builders of tomorrow
- [Visual Studio Code](https://docs.voqal.dev/library/applications/vscode.md)
- [Overview](https://docs.voqal.dev/library/overview.md): Teach your Voqal Assistant a wide range of tasks to perform autonomously
- [Gmail API](https://docs.voqal.dev/library/services/gmail_api.md)
- [Gmail](https://docs.voqal.dev/library/websites/gmail.md)
- [YouTube](https://docs.voqal.dev/library/websites/youtube.md)
- [Privacy](https://docs.voqal.dev/privacy.md): Your Voqal Assistant is personal and private
- [Quickstart](https://docs.voqal.dev/quickstart.md): Zero to natural speech programming in under 5 minutes

## OpenAPI Specs

- [openapi](https://docs.voqal.dev/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/voqal/voqal)
- [YouTube](https://www.youtube.com/channel/UCHalNmlP60aYn-qffa0P5eA)
- [Discord](https://discord.gg/KgTkR5Rffz)