Feature Requests
Roadmap
Changelog

February 10th, 2025

What's New in Synthflow: Flow Designer, New Copilot, RingCentral, GPT 4.5, Updated UI for Agencies & More

We’re excited to introduce significant changes that radically enhance how you work in Synthflow!

Flow Designer Available to All

Our next-generation conversational path tool is now open to everyone. 

  • Visually Map Dialogues: Drag, drop, and connect steps intuitively

  • Custom API Integration: Trigger workflows or pull data from third-party services

  • Native Actions: Add transfers, bookings, or notifications with a click

  • Context-Aware Precision: Build smarter branches and keep conversations predictable

  • Fast Iteration: Test, tweak, and optimize flows in real time

Introducing the Form-Based Copilot

We’re rolling out a new Copilot experience: you fill out a form, we generate the agent according to your specifications.

Copilot has 4 pages:

  1. Call Objectives: A multiselect list of call objectives

  2. General Information: Three text fields (company info, target audience, objection handling)

  3. Generate Prompt: A call-to-action to generate the prompt

  4. Review: A text box to edit or finalize the generated prompt

Note: If you plan on using appointment booking or call transfer, set those up first to ensure the prompt reflects those features.

The copilot uses the OpenAI reasoning model (o1), so prompt generation may take some time.

RingCentral Contact Center Integration

We’ve officially integrated with RingCentral Contact Center, making it easier than ever to supercharge your operations with Voice AI Agents. Now, you can seamlessly deploy AI-powered agents on top of your RingCentral infrastructure—handling overflow calls, after-hours inquiries, and more.

Why RingCentral Users Will Love This Integration:

  • Fast Deployment – Quickly launch inbound or outbound AI agents within your existing RingCentral setup.

  • Train Once, Assist Forever – No employee turnover. Connect your knowledge base, and AI handles the rest.

  • No Workforce Constraints – Scale effortlessly without hiring, training, or burnout—AI agents work 24/7.

  • AI That Follows Protocol – Handle complex requests, follow workflows, and ensure compliance in real time.

This means faster resolutions, improved efficiency, and happier customers. Ready to scale with Synthflow? 🚀

Agency UI Updates

Managing subaccounts is now faster, smarter, and more intuitive. We’ve reworked key areas to give you better control, improved structure, and a seamless experience.  

What’s New:  

  • Effortless Subaccount Creation – Instantly create multiple subaccounts at once, streamlining onboarding.  

  • Redesigned Pricing Plans – Set up and manage pricing plans faster with a more intuitive workflow.  

  • Seamless Product Imports – A smoother, more reliable experience when importing products to subaccounts.  

  • Smarter Permissions – A clearer, more structured way to assign and manage subaccount permissions.  

  • Powerful Limits & Defaults – A brand-new page to set restrictions for free-tier subaccounts, controlling access to calls, AI assistants, and workflows until they upgrade.  

  • Clear Subscription Management – A reworked view that makes it easy to see exactly what plan a subaccount is on.  

This is the biggest update to subaccounts yet—giving you more control, clarity, and efficiency.

Comprehensive Error Details in Your Logs

Full error messages are now clearly displayed in call logs, making it easier to spot issues, streamline debugging, and provide more accurate information for support.

VoiceTech Improvements

Active Listening Toggle
We now offer an active listening toggle for natural backchanneling, adding “um” and “uh” to make interactions feel more human.

New ElevenLabs Flash Models
We introduced eleven_flash_v2_5 (multilingual) and eleven_flash_v2 (English only), significantly reducing latency.

Overall Voice Engine 2.0 Upgrades
Our Voice Engine 2.0 engine provides consistently low latency, avoids repetitive responses, handles background noise better, supports multiple languages, and executes actions/webhooks more accurately.

Webhook Security

We’ve added HMAC signatures to validate webhook payloads. You can generate a secret key in Synthflow (unique per workspace), and we’ll combine the call ID with that key to create an HMAC-SHA256 signature. The signature is sent in the HTTP_SYNTHFLOW_SIGNATURE header—recreate and compare it on your end to confirm authenticity. All signatures are base64-encoded and keys are 256-bit for robust security. Read more in our docs.

Top-Up Wallet for PAYG

Pre-Charged Minutes: For pay-as-you-go and agency accounts, we’ve switched from post-usage purchases to always pre-charging for minutes—nothing else changes in your workflow.

Added GPT-4.5

Build Voice Agents using the latest model from OpenAI. GPT 4.5 provides enhanced reasoning, deep context comprehension, advanced instruction-following capabilities, but slightly slower performance.

Plan & Billing UI rework

We’ve refreshed the interface to make managing your subscription and comparing plans much clearer. Now you can:

• Instantly see what plan you’re on, with all the essential details

• Quickly compare every available plan in a single, clean view

Clearer Minute Tracking

We’ve introduced a clearer, better, and more transparent system to monitor minutes across both workspaces and subaccounts.

Other Updates

  • Pre-Charged Minutes: For pay-as-you-go and agency accounts, we’ve switched from post-usage purchases to always pre-charging for minutes—nothing else changes in your workflow.

  • Fraud detection & scammer account suspension: if you’re blocked you will be notified by email.

  • V2 Assistant CPS rate-limit error—fixed

  • Unknown V2 calls status fixed

  • Hubspot info extractor automate Sync—fixed Pablo

  • Correctly update the Synthesizer language via API—fixed

  • Numerous other changes for reliability and scalability




Write a comment...