The Three Modules
| Module | What it does | Where to configure |
|---|---|---|
| STT (Speech-to-Text) | Converts your voice to text | Settings → Model Config / Pro Creation |
| TTT (Text-to-Text / LLM) | Processes text and generates responses | Settings → Model Config / Pro Creation |
| TTS (Text-to-Speech) | Converts responses back to speech | Settings → Model Config / Pro Creation |
Global Model Configuration
Go to Dashboard → Settings → Model Configuration to set defaults for all Agents.- STT Platform / Model: Choose the transcription provider (e.g., Assembly) and model.
- TTT Platform / Model: Choose the LLM provider (e.g., OpenAI) and model (e.g., GPT-4).
- TTS Platform / Model: Choose the voice synthesis provider (e.g., ElevenLabs) and model.
- Play Filler Audios: Toggle to play short filler sounds while the system processes speech.
- Auto Sleep: Enable automatic sleep mode after a period of inactivity.
- Auto Sleep Timeout: Set the silence duration (in seconds) before the Agent confirms inactivity.
- FuzzyWuzzy Threshold: Adjust sensitivity of text-matching. Higher = stricter matching.
LLM Fine-Tuning Parameters
- Temperature: Controls response randomness. Lower (closer to 0) = more focused and deterministic. Higher (up to 1) = more creative and varied.
- Frequency Penalty: Reduces repetition of words and phrases. Higher values discourage repeating the same content.
- Presence Penalty: Discourages the model from introducing irrelevant topics. Higher values keep the LLM on subject.
Voice Fine-Tuning Parameters
- Voice Similarity Boost: Adjusts how closely the voice matches its intended sound. Higher = more consistent to the original voice.
- Voice Stability: Controls voice consistency. Lower = more varied and expressive. Higher = more stable and monotone.
Per-Agent Voice Configuration
When creating or editing an Agent in Pro Creation, configure voice under Personality Identity:- Voice Identity: Select from the available voices or enter a custom Voice ID from your TTS provider.
- Clone Voice: Use voice cloning to create a personalized voice.
- Preview: Play back the selected voice before saving.
Adding a Custom Voice
To add a custom voice from your TTS provider:- Go to the Agents dashboard and click the
button at the top right. - Fill in:
- Name: Identifies the voice in your list.
- Description: Tone, accent, or intended use.
- Voice ID: The Voice ID from your TTS provider (e.g., ElevenLabs).
- Click
to add the voice, or 
to discard.
Getting a Voice ID
Before adding a voice in OpenHome, upload your custom voice to your preferred TTS provider (e.g., ElevenLabs). Once uploaded, you’ll receive a Voice ID to enter in the field above.API Keys for Providers
Each provider (ElevenLabs, OpenAI, Assembly, etc.) requires an API key. Manage these under Settings → API Keys.When you update API keys, your Agents consume credits from the associated services. OpenHome is not responsible for charges from third-party providers.See Dashboard for full API key management details.