> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trugen.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Providers

> The external AI engines that power speech, language, and voice in TruGen's pipeline.

TruGen integrates with industry-leading AI providers to power each stage of the conversational pipeline. Each provider handles one capability — STT, LLM, or TTS — and can be configured independently per agent.

## Speech-to-Text (STT)

| Provider        | Model              | Best For                                                                                             |
| --------------- | ------------------ | ---------------------------------------------------------------------------------------------------- |
| **ElevenLabs**  | Scribe V2 Realtime | Ultra-low latency real-time transcription across many languages for live conversational applications |
| **Deepgram**    | Nova-3             | Real-time, multilingual, or complex audio scenarios requiring maximum accuracy and customisation     |
| **Deepgram**    | Nova-2             | High-volume, English-focused transcription where speed and low cost are the top priorities           |
| **Deepgram V2** | Flux General       | Real-time voice agents needing accurate transcription with intelligent turn detection                |

## Large Language Models (LLM)

| Provider              | Model                         | Best For                                                                   |
| --------------------- | ----------------------------- | -------------------------------------------------------------------------- |
| **Groq**              | GPT OSS 20b                   | Low-latency conversational AI and agents where fast responses are critical |
| **Groq**              | GPT OSS 120b                  | Higher-quality reasoning with low latency for more complex tasks           |
| **Groq**              | Llama-4 Scout                 | Multi-document analysis, codebase reasoning, and personalised tasks        |
| **Azure OpenAI**      | GPT-5.4-Mini                  | Fast, cost-efficient general-purpose language generation                   |
| **Azure OpenAI**      | GPT-5.4-Mini Medium Reasoning | Balanced reasoning for structured and multi-step tasks                     |
| **Azure OpenAI**      | GPT-5.4-Mini Low Reasoning    | Ultra-fast responses for simple conversational tasks                       |
| **Google**            | Gemini 3.1 Pro Preview        | Advanced reasoning and high-quality generation for complex tasks           |
| **Google**            | Gemini 3.1 Flash Lite         | Fast, lightweight responses for cost-sensitive deployments                 |
| **Open Router**       | Llama 4 Scout                 | Open-source model access via a unified routing layer                       |
| **Open Router**       | GPT OSS 120B                  | Large open-source model via routing layer                                  |
| **Livekit Inference** | Gemma 4 31b                   | Edge-optimised inference for low-latency deployments                       |

## Text-to-Speech (TTS)

| Provider       | Model     | Best For                                                                     |
| -------------- | --------- | ---------------------------------------------------------------------------- |
| **ElevenLabs** | Turbo 2   | Fast, low-latency English TTS for real-time voice agents and IVR systems     |
| **ElevenLabs** | Turbo 2.5 | Fast, low-latency multilingual TTS for real-time conversational AI           |
| **Cartesia**   | Sonic 3   | Real-time conversational TTS with a wide range of expressive voices          |
| **Cartesia**   | Sonic 3.5 | Next-generation real-time TTS with enhanced voice quality and expressiveness |

<Note>New providers and model configurations are added regularly. Use the `/v1/providers` endpoint to always fetch the latest available list.</Note>

## Provider Types

| Type  | Role                                                     |
| ----- | -------------------------------------------------------- |
| `llm` | Large Language Model — reasoning and response generation |
| `stt` | Speech-to-Text — real-time audio transcription           |
| `tts` | Text-to-Speech — voice rendering                         |

## Retrieve All Providers

Use this endpoint to fetch all currently available providers and their models:

**GET** `/v1/providers`

<CodeGroup>
  ```bash Request theme={null}
  curl --request GET \
    --url https://api.trugen.ai/v1/providers \
    --header 'Content-Type: application/json' \
    --header 'x-api-key: <api-key>'
  ```
</CodeGroup>

<Note>Replace `<api-key>` with your API key from the Developer Portal.</Note>

## What's Next?

<CardGroup cols={2}>
  <Card title="Bring Your Own LLM" icon="brain" href="/docs/resources/byo-llm">
    Connect a self-hosted or custom LLM to your agents.
  </Card>

  <Card title="Multilingual Support" icon="globe" href="/docs/agents/multilingual-support">
    Configure STT and TTS languages for global conversations.
  </Card>

  <Card title="Create Agent" icon="robot" href="/api-reference/endpoint/agentcreate">
    Assign provider selections when creating a new agent.
  </Card>

  <Card title="Providers API Reference" icon="book" href="/api-reference/endpoint/providerget">
    Full endpoint documentation for retrieving provider information.
  </Card>
</CardGroup>