How to integrate Voice Technologies (Speech-to-Text, Text-to-Speech)
The AI agent can also understand voice queries (Speech-to-Text or STT) and respond with voice (Text-to-Speech or TTS), for example, during phone calls or via a voice interface.
Flametree supports integration with any external voice models compatible with OpenAI-like APIs (e.g., Azure Speech, Eleven Labs).
Speech-to-Text (STT) Integration
This integration allows the AI agent to transcribe user speech into text. It is used in voice channels (e.g., SIP, Twilio) and in the Playground interface when the microphone is enabled.
Steps:
- Go to the Integrations section
- Find the Speech-to-text (STT) integration type and click Add +
- Fill in the following fields:
| Field | Description |
|---|---|
| Name, Description | Custom name and description of the integration |
| OpenAI-compatible API URL | Speech recognition server URL |
| Access Token | API access token from the provider |
| Type | Type of the integration e.g. whisper, local_whisper, 3i-vox |
| STT Model Name | STT model name. For local_whisper e.g. whisper-large, whisper-medium, whisper-small |
- Click Save
Text-to-Speech (TTS) Integration
This integration allows the AI agent to speak responses out loud. It is used during phone calls or when voice playback is enabled in the Playground.
Steps:
- Go to the Integrations section
- Find the Text-to-speech (TTS) integration type and click Add +
- Fill in the following fields:
| Field | Description |
|---|---|
| Name, Description | Custom name and description of the integration |
| OpenAI-compatible API URL | URL of the speech synthesis server |
| Access Token | API access token from the provider |
| TTS Model Name | Voice model name (e.g., Polly.Salli, en-US-JennyNeural) |
| Voice Provider | e.g., azure, elevenlabs depending on the platform |
| Region (optional) | For Azure: eastus, westeurope, etc. |
- Click Save
Supported Platforms
Currently tested and supported:
- OpenAI Whisper
- Google Speech-to-Text (v2)
- Azure Cognitive Services (Speech)
- Eleven Labs (TTS)
Important Notes
- A single AI agent can use different voice models for STT and TTS.
- If you are using Twilio, there is no need to configure TTS/STT separately — Twilio uses its own built-in voice engines.
- For SIP integration, you must configure STT and TTS manually.