Documentation / How Tigy AI Works

How Tigy AI Works

The big picture — from API call to phone conversation to transcript

Tigy AI is a platform for building and running voice AI agents. You define a conversation flow, connect a phone number, and Tigy AI handles the rest — transcribing the caller's speech (STT), generating intelligent responses (LLM), speaking them back in a natural voice (TTS), and returning structured results when the call ends.

The core loop```mermaid

sequenceDiagram participant U as Dashboard / Your App participant API as Tigy AI API participant STT as Transcriber (STT) participant LLM as LLM Provider participant TTS as Voice Synthesizer (TTS) participant Tel as Telephony Provider participant Cal as Caller / Contact

U->>API: Start a conversation
Tel->>Cal: Caller connects
Tel-->>API: Raw audio stream
loop Conversation
    API->>STT: Caller audio
    STT-->>API: Transcribed text
    API->>LLM: Transcript + agent prompt + context
    LLM-->>API: Agent response text
    API->>TTS: Response text
    TTS-->>API: Synthesized audio
    API->>Tel: Audio stream
    Tel->>Cal: Agent speaks
end
API->>API: Extract context, run webhooks
API-->>U: Run record (transcript, recording, gathered data)


**[Runs](/core-concepts/calls-and-runs)**
Every execution of a agent creates a run. The run record holds the transcript, recording, extracted data, and cost information.

**[Telephony](/integrations/telephony/overview)**
The phone infrastructure. Tigy AI connects to your telephony provider to receive calls and stream audio between the caller and your agent in real time.

**[Transcriber (STT)](/configurations/transcriber)**
Converts the caller's speech to text in real time. Tigy AI sends the audio stream to your configured speech-to-text provider and uses the transcript to drive both the LLM and the final run record.

**[LLM Provider](/configurations/llm)**
Processes the transcript and the agent's prompt to generate the agent's next response. It follows the agent instructions and can call the configured tools.

**[Voice Synthesizer (TTS)](/configurations/voice)**
Converts the LLM's text response to audio and streams it back to the caller. The choice of TTS provider and voice is configurable per agent.

## How it fits together

When you trigger a call:

1. Tigy AI instructs your telephony provider to dial the number
2. When the caller answers, a real-time audio pipeline opens
3. The caller's speech is transcribed by the STT provider
4. The transcript is sent to the LLM with the agent's prompt and conversation history
5. The LLM responds — the response is synthesized to audio by the TTS provider and streamed to the caller
6. The conversation continues according to the agent instructions until the caller hangs up, the end-call tool is invoked or a configured limit is reached
7. Post-call: context is extracted, webhooks fire, the run record is saved

## Next steps

**[Calls & Runs](/core-concepts/calls-and-runs)**

The lifecycle of a call

← Back to documentation

The core loop```mermaid

U->>API: Start a conversation Tel->>Cal: Caller connects Tel-->>API: Raw audio stream loop Conversation API->>STT: Caller audio STT-->>API: Transcribed text API->>LLM: Transcript + agent prompt + context LLM-->>API: Agent response text API->>TTS: Response text TTS-->>API: Synthesized audio API->>Tel: Audio stream Tel->>Cal: Agent speaks end API->>API: Extract context, run webhooks API-->>U: Run record (transcript, recording, gathered data)

**[Runs](/core-concepts/calls-and-runs)** Every execution of a agent creates a run. The run record holds the transcript, recording, extracted data, and cost information. **[Telephony](/integrations/telephony/overview)** The phone infrastructure. Tigy AI connects to your telephony provider to receive calls and stream audio between the caller and your agent in real time. **[Transcriber (STT)](/configurations/transcriber)** Converts the caller's speech to text in real time. Tigy AI sends the audio stream to your configured speech-to-text provider and uses the transcript to drive both the LLM and the final run record. **[LLM Provider](/configurations/llm)** Processes the transcript and the agent's prompt to generate the agent's next response. It follows the agent instructions and can call the configured tools. **[Voice Synthesizer (TTS)](/configurations/voice)** Converts the LLM's text response to audio and streams it back to the caller. The choice of TTS provider and voice is configurable per agent. ## How it fits together When you trigger a call: 1. Tigy AI instructs your telephony provider to dial the number 2. When the caller answers, a real-time audio pipeline opens 3. The caller's speech is transcribed by the STT provider 4. The transcript is sent to the LLM with the agent's prompt and conversation history 5. The LLM responds — the response is synthesized to audio by the TTS provider and streamed to the caller 6. The conversation continues according to the agent instructions until the caller hangs up, the end-call tool is invoked or a configured limit is reached 7. Post-call: context is extracted, webhooks fire, the run record is saved ## Next steps **[Calls & Runs](/core-concepts/calls-and-runs)** The lifecycle of a call