On air · voice agent runtime Inbound · outbound · sub-second

Voice agent API · studio · telephony

Keep the line. Finish the task.

Quoral is a core AI/ML product: a voice agent API and studio for inbound and outbound phone work. Teams write flows, tools, and knowledge once. Quoral runs turn-taking, telephony, and transcripts so every line stays under a second.

  • Voice agents inbound + outbound
  • Turn-taking under a second
  • Models Claude, GPT-4o, Llama, Nova
Claude 3.7 SonnetGPT-4oLlama 3 70BAmazon NovaBedrockAnthropicOpenAI DirectGroqBedrock AgentCore Claude 3.7 SonnetGPT-4oLlama 3 70BAmazon NovaBedrockAnthropicOpenAI DirectGroqBedrock AgentCore

AI features

Where the voice agent actually sits

Quoral is in the business of building a core AI/ML product. These named jobs are first-class on the line: the agent runtime, the models it can call, and the telephony that carries them. This is a voice agent company — not a chat widget bolted onto a number.

AI feature · Voice agent API

Inbound and outbound phone agents on one agent id

For teams that need a spoken agent on PSTN, SIP, or a WebSocket

Write flows, tools, and knowledge once. Quoral runs the agent on the live line. Studio and the API share the same agent id so a patch in the booth ships to production.

Flow + tools + knowledge → POST /v1/runs → live call

AI feature · Sub-second turn-taking

Barge-in, silence, and the next line under a second

For operators who cannot wait on a contact-center pause

Quoral owns turn-taking on the audio path. The caller can interrupt. Silence does not hang. Every spoken turn is designed to stay under a second.

PCM / RTP → turn-taking runtime → next utterance

AI feature · Model routing

Claude, GPT-4o, Llama 3 70B, and Amazon Nova

For platform teams picking speed on the spoken turn

Planned model families: Claude 3.7 Sonnet, GPT-4o, Llama 3 70B, Amazon Nova. Access paths: Bedrock, Anthropic, OpenAI Direct, Groq. Agent frameworks: custom/homebrew and Amazon Bedrock AgentCore. Quoral is not fine-tuning those models.

Agent turn → selected model → Bedrock / Anthropic / OpenAI / Groq

AI feature · Tools, RAG, transcripts

Function calls, site-synced knowledge, one call object

For builders who need the agent to book, look up, and hand off

Tool calls stream while the caller is still speaking. RAG syncs from your site onto the same agent. Transcripts, traces, and recordings land in one call object you can score.

Utterance → tool / RAG → transcript on the call object

IVA platform. Speech recognition, chat, and customer-support voice. MVP stage — no invented customers, funding, or uptime claims on this page. Models are consumed, not trained here.

Method

How Quoral ships

Write the job once. Attach a number. Keep a call object you can score.

01

Write the chorus.

Describe the job, the tools, and the knowledge source. Version it in Studio.

02

Open the line.

Attach a number or a WebSocket. Quoral handles barge-in and silence.

03

Keep the record.

Transcripts, traces, and recordings land in one call object you can score.

Stack

What you actually buy

A voice agent runtime. Studio, telephony, and the call object — not a trained foundation model.

Flows

Draw branches, barges, and handoffs. Guardrails sit on the same graph the runtime executes.

Line stack

PSTN, SIP, and branded caller ID. Quoral owns the audio path and keeps PCM and RTP inside the API.

Tools

Book, pay, look up, transfer. Function calls stream while the caller is still speaking.

Studio

Listen to a call, patch a prompt, ship a version. Eval sets ride with the same agent id.

Start

A live number in one afternoon.

Write founder@quoral.site. You get a test token, a sample inbound flow, and a 30-minute walkthrough on the line you want to run.

See pricing