Talkative Voice AI Support

Welcome to the Talkative Voice AI support page. Here you’ll find everything you need to get started with our innovative Voice AI solution, including setup instructions, how it works, integration details, and troubleshooting tips.

Overview

Talkative Voice AI is an advanced, real-time voice assistant designed to handle incoming calls, capture conversation details, and even transfer calls when needed. Built with state-of-the-art speech-to-text (STT), large language models (LLM), and text-to-speech (TTS) technology, Voice AI delivers natural, conversational interactions for a range of use cases - from scheduling callbacks to confirming appointment details.

Voice AI bots can:

• Answer inbound calls automatically

• Capture key information using AI (like name, reference number, etc.)

• Lookup answers from your AI Knowledge Base

• Use custom flows and fallback logic to route customers to the right outcome

• Escalate to human agents when needed

Please Note: Our Voice AI solution is currently in beta. We’re continually refining the system to ensure the best possible performance.

Getting Started

Setting Up Your Voice AI

1. Fill Out The Form Below

   Please reach out to Talkative to configure Voice AI in your account.

2. Access Your Settings:

   Log in to your Talkative account and search for “voice” in the settings menu to go to Voice AI Configs.

3. Create Your Voice AI Configuration:

   • Max Duration: Specify the maximum duration (in seconds) for a call.
   • Introduction: Enter the greeting that your Voice AI will use (for example, “Hi, thanks for calling Talkative. How can I help you today?”).
   • Prompt: Provide the instructions for your Voice AI. Tip: For best results, if you’re configuring Voice AI for a specific language, write the prompt in that language.

4. Configuration Outcome:

   Once set up, your configuration automatically creates a dedicated queue and user for handling voice interactions.

How It Works

Voice AI transforms your incoming calls into actionable conversations by following these steps:

1. Voice Input & Transcription:
   • Your caller’s voice is converted into text using our advanced speech-to-text service.
2. AI Processing:
   • The transcribed text is sent to a large language model (LLM) that generates a contextually appropriate response based on your prompt.
3. Response Delivery:
   • The response text is converted into voice using our text-to-speech system and played back to the caller in real time.
4. Call Transfer:
   • When necessary, the system can transfer the call. A special trigger phrase (for example, __TRANSFER__) initiates the transfer process to your designated phone queue or extension.

Integration with your Phone System

Voice AI can be used to send calls into any phone system by sending in calls via PSTN. Additionally, for a tighter integration, SIP-integration is possible. The below list of “advanced” phone system integrations are possible, with the list planned to expand over time:

• Mitel Integration:

  For customers with Mitel, our integration requires a simple IVR application setup. Calls are routed via SIP traffic, and our system works seamlessly with your existing Mitel setup - ensuring that caller ID is retained and a summary of the conversation is available to your agents.

Call Flow & Interaction Summary

Here’s how a typical call is handled:

1. Call Initiation:

   A caller dials your Voice AI number.

2. Interaction with Voice AI:

   • The Voice AI greets the caller.
   • The conversation is transcribed in real time.
   • Depending on the situation, the system either handles the call or initiates a transfer.

3. Call Transfer & Agent Support:

   When the conversation requires human intervention, the call is transferred (using SIP Refer) to your agent’s queue. Agents can view a screenpop showing a summary and full transcript of the conversation.

Voice selection and language support

VoiceAI supports a wide range of languages and voices. You can choose from a variety of voice options within the bot editor, including different accents, genders, and tones.

We readily support the following languages by default:

• English

• Dutch

• German

• Portuguese

• Finnish

If you need to support other languages, we can enable additional voices upon request. The extended list of supported languages includes:

• Arabic

• Bulgarian

• Chinese (Simplified)

• Chinese (Traditional)

• Chinese (Traditional, Taiwan)

• Czech

• Danish

• Estonian

• French

• French (Canadian)

• Italian

• Japanese

• Norwegian

• Polish

• Portuguese (Brazilian)

• Russian

• Spanish

• Spanish (Latin America and the Caribbean)

• Swedish

• Taiwanese

• Welsh

Voice AI Playground

You can test your Voice AI bot directly in your browser using the Voice AI Playground. Just go to your Voice AI configuration and click “Test your Voice AI Bot”. This will launch an in-browser simulation that lets you try out your bot in real time - ideal for checking knowledge base lookups, call flows, and voice performance.

Note: If you want to test a different voice, make sure to first select your preferred voice in the Voice field, click Save, and then re-enter the bot configuration. The playground will then reflect the updated voice selection.

Using Tools in Voice AI

Voice AI now supports tools - structured actions that the AI can call during a conversation. These go beyond natural language responses, allowing your Voice AI to:

• Transfer the customer to another department or queue

• End the call

• Search your Knowledge Base directly

• Make external API calls

• Book or retrieve calendar slots using Cal.com

These tools can be configured in the Voice AI bot builder under the Tools section. For full details on tool setup, prompts, and required parameters, see our configuration guide here.

Frequently Asked Questions (FAQs)

Q1: What happens if my caller speaks in a language other than what’s configured?

A: While Voice AI can handle multiple languages, we recommend setting up one language per phone number to ensure the highest accuracy. If your callers use multiple languages, please contact support for guidance on configuration options.

Q2: Can I customize the voice and accent?

A: Yes! You can choose from a variety of voices and accents. We highly recommend testing different options to see which best represents your brand’s tone.

Q3: Is call recording available?

A: Absolutely. For the best troubleshooting and quality control during beta, please ensure that call recording is enabled in your Company Config.

Q4: How do I initiate a transfer?

A: When the AI identifies that a transfer is needed, it will include the special trigger text (__TRANSFER__). This initiates a transfer to your configured queue or extension.