> For the complete documentation index, see [llms.txt](https://project-45.gitbook.io/tavus/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://project-45.gitbook.io/tavus/conversational-video-interface/custom-stt-onboarding.md).

# Custom STT Onboarding

You can choose between `tavus-turbo` and `tavus-advanced` as your STT engine, and adjust the VAD sensitivity to your needs.

### [​](https://docs.tavus.io/sections/conversational-video-interface/custom-stt-onboarding#create-persona)Create Persona <a href="#create-persona" id="create-persona"></a>

To get started, you’ll need to create a Persona that specifies your STT engine and VAD sensitivity. Here’s an example Persona:

```json
{
    "system_prompt": "You are a storyteller. You like telling stories to people of all ages. Reply in brief utterances, and ask prompting questions to the user as you tell your stories to keep them engaged.",
    "context": "Here are some of your favorite stories: Little Red Riding Hood, The Ugly Duckling and The Three Little Pigs",
    "persona_name": "Mert the Storyteller",
    "layers": {
        "llm": {
            "model": "custom_model_here",
            "api_key": "example-api-key",
            "base_url": "open-ai-compatible-llm-http-endpoint",
            "tools": [<your-tools-here>],
            "speculative_inference": true,
        },
        "tts": {
            "api_key": "example-api-key",
            "tts_engine": "playht",
            "playht_user_id": "your-playht-user-id",
            "external_voice_id": "professional-voice-clone-id",
            "voice_settings": {}, // can also leave the "voice_settings" attr out if you want to use default settings
            "tts_emotion_control": false
        },
        "vqa": {
            "enabled": false // can also leave the "vqa" attr out if you want vqa enabled
        },
        "stt": {
            "participant_pause_sensitivity": "medium",
            "participant_interrupt_sensitivity": "medium",
            "stt_engine": "tavus-advanced",
            "hotwords": "This is a hotword example",
        }
    }
}
```

`<persona created>, id: p234324a`

### [​](https://docs.tavus.io/sections/conversational-video-interface/custom-stt-onboarding#stt-engine)STT Engine <a href="#stt-engine" id="stt-engine"></a>

The STT engine parameter controls the transcription engine that will be used. The default is `tavus-advanced`, but you can adjust this to `tavus-turbo` for a tiny latency improvement. However, `tavus-advanced` provides much higher transcription accuracy and supports non-English languages, so we highly recommend using it for almost all use cases.

### [​](https://docs.tavus.io/sections/conversational-video-interface/custom-stt-onboarding#speech-sensitivity)Speech Sensitivity <a href="#speech-sensitivity" id="speech-sensitivity"></a>

These sensitivity parameters control the sensitivity of the Voice Activity Detection (VAD) engine. The defaults are `medium`, but you can adjust this to `low` or `high` depending on your needs. You can use the guidelines below to choose the right sensitivity for your use case:

#### [​](https://docs.tavus.io/sections/conversational-video-interface/custom-stt-onboarding#participant-pause-sensitivity)Participant Pause Sensitivity <a href="#participant-pause-sensitivity" id="participant-pause-sensitivity"></a>

Controls how long of a pause the user can take before the replica responds. You can think of this as the replica’s “pause” tolerance.

* **low:** A low sensitivity means you can take longer pauses before the replica responds. Use this for slower, more thoughtful conversations.
* **medium:** The default behavior. A nice balance between responsiveness and thoughtful pauses.
* **high:** A high sensitivity means the replica responds very quickly to the user’s speech. Use this for fast, chatty conversations, where small pauses from the participant will trigger a response.

#### [​](https://docs.tavus.io/sections/conversational-video-interface/custom-stt-onboarding#participant-interrupt-sensitivity)Participant Interrupt Sensitivity <a href="#participant-interrupt-sensitivity" id="participant-interrupt-sensitivity"></a>

Controls how long the user can speak before the replica will be interrupted. You can think of this as the replica’s “interrupt” tolerance.

* **low:** A low sensitivity means you can talk longer before the replica will stop talking and listen. Use this for slower, more thoughtful conversations.
* **medium:** The default behavior. A nice balance between responsiveness and tolerance of short affirmations.
* **high:** A high sensitivity means the replica will stop talking very quickly when the user speaks. Use this for fast, chatty conversations, where small responses from the participant will trigger a new response from the replica.