Changelog
Follow new updates and improvements to Synthflow.
June 4th, 2025
We’ve added some great new features to Synthflow this May — including warm transfers with helpful context, improved SIP routing, and clearer error handling — all designed to help you work faster and troubleshoot smarter.
We’ve expanded our call transfer capabilities. You can now performWarm Transfers with a Contextual Summary allowing your AI agent to hand off calls to a human agent with a real-time summary of the conversation. This ensures smoother transitions and better customer experiences.
We now support:
Cold Transfer: Immediate, no message is played to the human receiving the call.
Warm Transfer with Message: You can configure a hard coded message to be played to the human receiving the call.
Warm Transfer with Contextual Summary: Our AI will automatically summarise the conversation between your customer and Synthflow when handing over to your human agent.
Read more in the documentation.
Want to learn how to make the most of warm transfers? Join our special live session with Kevin on Friday June 6.
In this live session, Kevin will guide you through building flows that pass context before your Voice Agent transfers a client to a team member.
You can now use Diversion headers to route inbound SIP calls with greater precision and context.
Unlike standard SIP headers, Diversion headers tell you where the call came from and why it was redirected. That’s crucial for call forwarding, transfers, and any flow where caller history matters.
Previously, routing relied on static SIP headers and rigid logic. Now, Diversion headers give you the flexibility to steer each call to the right Voice AI Agent, using richer context—all without breaking SIP protocol.
Note: Diversion headers work only for inbound calls.
Read more in the documentation.
Inbound Webhook with Custom Variables: customize inbound call behavior with dynamic variables. Use your Inbound Call Webhook to automatically manage call flows and apply context-specific logic.
Read the Inbound Webhook documentation.
Custom Action Messaging Control: We’ve added API support to give developers more control over how custom action messages behave. You can now:
Choose between LLM-generated or hardcoded messages
Set fallback messages for failed or delayed actions
Read more in the documentation.
We've enhanced how Twilio error codes are displayed in the dashboard. You can now view the End Call Reason to quickly identify if an issue was related to your Twilio setup.
In Case You Missed It: IVR Handling
Until now, outbound agents couldn’t get past IVR menus. When a call reached a phone tree — “Press 1 for sales, 2 for support” — the agent had no way to respond. That meant stalled flows, missed connections, and broken automation.
We’ve fixed that. With IVR Handling, outbound agents can now simulate keypresses to navigate DTMF‑based IVR systems automatically. Whether it’s a single prompt or a multi‑step phone menu, agents can now complete the flow end‑to‑end.
Have you had a chance to try IVR Handling yet? If not, check out our brand‑new tutorial video and see it in action:
May 9th, 2025
Hi everyone! April brought a wave of upgrades including Salesforce integration, IVR, GPT-4.1, custom action messages, and more.
Modernizing your Salesforce contact center just got simpler with Synthflow Voice AI Agents—now available on the AppExchange.
Automate customer calls, update CRM records in real time, and unlock a new era of customer service efficiency.
Deliver instant, voice-first support directly within Salesforce. With built-in telephony integration, you can turn your CRM into a real-time customer engagement engine.
Update contacts, cases, or custom fields automatically after every call—no manual work required.
Trigger outbound voice calls to inactive leads from Salesforce and convert outdated records into engaged prospects.
Until now, outbound assistants couldn’t get past IVR menus. When a call reached a phone tree — “Press 1 for sales, 2 for support” — the assistant had no way to respond. That meant stalled flows, missed connections, and broken automation.
We’ve fixed that.
With IVR Handling, outbound assistants can now simulate keypresses to navigate IVR systems automatically. Whether it’s a single prompt or a multi-step phone menu, assistants can now complete the flow end-to-end.
Currently in beta. For now, it only works for DTMF input (based on pressing digits), not vocal IVR trees. To learn more, see Set up IVR handling.
Users now have greater control over custom action messaging. They can:
Choose between LLM-generated context-aware messages or their own hardcoded messages.
Set a dedicated message to play if a custom action fails.
Set a dedicated message to play if a custom action is delayed.
GPT 4.1 and 4.1-mini
You are able to use GPT 4.1 and GPT 4.1-mini, the latest and best from OpenAI. Try these models for increased performance and speed.
(Enterprise) Dial to Sip Endpoint.
In scenarios where your telephony provider does not offer elastic SIP trunking or if you have a more complex telephony setup unsuitable for elastic SIP trunking, you can use direct SIP dialing to our endpoint.
In this scenario, Synthflow does not directly place or receive calls. Rather, your telephony system manages the dialing process to connect with the specified SIP endpoint. You will need to develop the integration logic tailored to your telephony provider's requirements. From Synthflow’s standpoint, all call interactions will be treated as incoming, so your integration must explicitly define call direction handling.
What Else Is New
Real-time booking feels more human, better email capture, and agents now switch between 10+ languages:
Improving Real-Time Booking: Agents now suggest booking slots faster, making the user experience more human then ever.
Improved email capturing. Improved accuracy in recognizing emails, especially in English.
Multi-language agents: Agents can now switch dynamically between 10+ languages including Spanish, French, German, Hindi, and more.
April 17th, 2025
Dear Customer,
In January, we released Voice Engine Version 2.0 — a major upgrade from the legacy Version 1.0. To ensure all users benefit from its improved performance, we will be sunsetting Version 1.0 on April 30, 2025. After this time, all existing agents will be automatically migrated to Version 2.0. You can also move the agents on your own to Version 2.0 before this date.
What’s new in Version 2.0:
✅ Advanced background noise & voice cancellation
✅ Adjustable voice speed
✅ Optional background noise
✅ -10% reduction in latency
✅ Enhanced voice recognition with -5% fewer missed words
✅ Smarter voicemail detection
✅ SIP trunking (Enterprise-only)
How to upgrade to Version 2.0:
For a quick step-by-step guide on how to upgrade your agents, see our documentation.
If you do nothing, all agents will automatically upgrade to Version 2.0 in early May.
If you have any questions, or trouble please contact us.
Kind Regards,
The Synthflow Team
March 27th, 2025
This release is packed with features that make building and scaling with Synthflow smoother than ever. We’ve improved transcription by 25%. Flow Designer now supports autosave and autocomplete, assistant actions are easier to transfer between subaccounts, and agency pricing plans now support multi-currency billing. We’ve also rolled out API improvements, bug fixes, and enabled Krisp by default for crystal-clear calls.
Deployed Nova-3
We’ve integrated Deepgram Nova-3, the world's leading transcription model that reduces errors in English-language transcription by 25% compared to Nova-2, our previously used model. To ensure maximum performance and speed, we’ve deployed the model on our own servers.
Flow Designer Autosave and Autocomplete
Flow Designer now includes autosave, along with autocomplete support for actions, variables, and results—making it faster and easier to build and edit flows.
Subaccount Action Importing and Concurrency Limits
Subaccount Action Importing
Actions can now be imported into subaccounts by importing an assistant. All associated actions will transfer automatically—except for appointment booking actions, which must be configured separately.
Subaccount Concurrency Limits
You can now define a concurrency limit when creating a subaccount to control the maximum number of concurrent calls. Use the optional concurrency parameter in the create-subaccount endpoint. (Docs)
Multi-Currency for Subscriptions and Rebilling
Pricing plans can now be created and billed in multiple currencies (EUR, CAD, USD). Subaccounts will be charged in the currency of the pricing plan they subscribe to. For example, if a plan is created in CAD, the subaccount will be billed in CAD for both the subscription and any usage-based charges.
Idle Parameter Configuration via API
Idle Parameters Configuration via API: You can now programmatically change the max idle duration, number of idle reminders, and the reminder message through the API. (Docs)
Fixed: 401 Error on Subaccount Phone Number Retrieval: Resolved an issue where API calls to retrieve a subaccount’s phone numbers were returning a 401 error.
Fixed: Missing Defaults for New Subaccounts: Agency-level limits and defaults are now correctly applied when creating a new subaccount via the API.
Improvements You’ll Notice
Better Knowledge Bases: Faster and more accurate retrieval.
Krisp Noise-Cancellation: Krisp is now enabled by default for all calls (excluding widgets), providing crystal clear audio clarity.
Custom Actions Documentation: Updated documentation is now available for building and integrating custom actions (Docs)
“Before the Call” Actions: These now trigger correctly, ensuring pre-call workflows execute as expected.
ElevenLabs Controls: Specify delivery, pronunciation, and emotion using ElevenLabs controls in the speech section of the custom action panel.
 Synthflow Academy: AI Trends & Challenges: Food Industry Edition |
Everyone wants a bite of the food industry — but applying AI at scale in one of the most operationally complex sectors is a tough dish to serve. |
March 19th, 2025
Say goodbye to background noise—Synthflow just got crystal clear with Krisp.ai.
Krisp.ai Noise Cancellation
Synthflow has integrated Krisp.ai’s advanced Background Voice and Noise technology into our Voice AI Real-Time Phone Agent, ensuring crystal-clear audio quality during all customer interactions.
Key Benefits:
Enhanced Call Clarity: Cleanses audio in real-time, before ASR kicks in, for distraction-free conversations.
Improved AI Performance: Background voice and noise elimination improves turn detection and speech processing accuracy.
Results:
Up to 95% noise reduction in customer calls.
(On a side note) Join our CEO Hakob as he chats with Davit, CEO and Co-founder of Krisp, about overcoming noise challenges in voice AI on Thursday 27th March. Register now.
Flow Designer Updates
We've enhanced usability and workflow management in Flow Designer:
New search bar for quick action selection.
FAQ descriptions now guide clearer AI responses.
Unified "Add" buttons with distinctive purple '+' icon.
Improved node visibility and highlighting.
Zoom level capped at 120% for optimal navigation.
Clear notifications for node actions (copy, paste, delete).
Increased visibility for "During the Call" actions in the Flow Designer.
Better Integrations & API Key Management
We've updated the API keys management and Integrations interface to streamline usability:
Added the option to give names and descriptions to API keys for improved organization
More organized Integrations with a consistent experience across the app.
Improved the interface of Integrations for subaccounts (Agency only).
Upcoming API Key usage tracking feature for better visibility and management.
If you want to refresh your knowledge of using APIs in Synthflow, be sure to check out the brand-new Custom Actions course in the Synthflow Academy.
Miscellaneous Updates
Enabled HubSpot integration for subaccounts.
Support to add multiple actions to an assistant at once.
Enhanced webhook data with team details (GHL integration).
Updated HubSpot and GHL integrations to api.synthflow.ai endpoint.
Enforced secure password policy for email sign-ups.
Enhanced Voicemail Detection:
Our voicemail detection is now more accurate! We now analyze the raw audio—including pauses and intonation—to identify real leads
UX and Platform Enhancements:
Assistants now displayed in the Workflows table.
Improved empty state design for Workflows and Subaccounts pages.
Telephony alerts for phone number changes (Enterprise only).
Support for free pricing plans creation (agency accounts).
Clearer Stripe error messages.
Clearer and more informative experience when creating Knowledge Bases.
Default permissions for new subaccounts use the settings applied to the last subaccount updated.
Streamlined bulk permissions management directly from the subaccounts page.
Option to select unique identifiers (phone/mobile) for HubSpot sync.
Bug Fixes:
Disconnecting your Twilio account keeps your phone numbers using Voice Engine 2.0 properly configured.
February 10th, 2025
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:
Call Objectives: A multiselect list of call objectives
General Information: Three text fields (company info, target audience, objection handling)
Generate Prompt: A call-to-action to generate the prompt
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
February 5th, 2025
We’re super excited to bring you major updates that’ll massively improve your workflows in Synthflow and beyond!
Don’t get left out…these are the changes that we’ve made in this release 👇
Interface Improvements including new Custom Actions UI and more
Consent Toggle and API for Recording and Transcription
20+ New Languages including Swedish, Hindi, and German
Bigger, Better, Faster, Stronger Voice Engine 2.0
Hire an Expert: Form to Connect with Solution Partners for Same-Day Support
PAYG Top-Up System
Account Management: Cal.com for Subaccounts
Flow Designer Closed Beta — Request Access Now!
Trigger Batch Campaigns with Workflows
Scroll down to not be left behind on our changes…
Enterprise: Updated SIP URI, Telnyx and 3CX Integration
We’ve updated the SIP URI to sip:sipin.synthflow.ai:32681. If you’re using SIP trunking with Synthflow, update your configuration to maintain uninterrupted service.
We now support Telnyx and 3CX as a new SIP trunking integration, alongside Twilio and Vonage, making it easier to connect your preferred voice provider. SIP trunking allows enterprise customers to migrate existing phone numbers, integrate with their telephony provider, and scale communication with elastic SIP. Configure your trunk, point it to the new URI, and import your numbers into Synthflow for reliable, scalable connectivity.
Support for RingCentral is coming next week.
Contact our sales team to enable this feature.
New UI for Templates and Custom Actions, Quick Access to Action IDs, Improved Search
We’ve rolled out several updates to make your experience more intuitive and efficient:
Assistant Templates UI: The interface has been completely revamped as part of the new Synthflow Marketplace, aligning with the latest design standards to enhance usability and deliver a seamless experience. Submit your templates until the end of February to be considered for the Marketplace Launch Contest.
Custom Actions UI: When creating a new custom action, you now have access to Marketplace Action Templates and a step-by-step Action Setup UI to simplify the process.
Assistant Filters Now Available: Users can filter their assistants on the main page by assistant type, template status, voice engine version (1.0 or 2.0), and phone number for easier management.
Improved Search & Filtering: The Actions interface now supports better search and filtering functionality.
Quick Access to Action IDs: Copy Action IDs directly from the 3-dots menu.
Improved Error Emails: Notifications about errors now include more detail.
These updates are designed to give you more control, streamline navigation, and enhance overall usability.
Consent Toggle and API for Recording and Transcription
Users can now enable or disable consent settings for recordings and transcriptions for agents using Voice Engine 1.0 in the Configure Tab of the assistant. If the recording consent is enabled, the Agent will evaluate if the user gave the consent or not to record the call. If the user consent is given, the Agent will automatically start recording the call.
This feature is also available via our agents API:
• consent_recording (boolean) – Enable or disable recording consent.
• consent_text (string) – Custom message for the consent request.
These fields are supported in POST and PUT requests when updating an agent.
For more details on implementing this via API, refer to the SynthFlow API documentation.
20 + Languages
We now support transcription and voice synthesis for over 20 new languages, including Swedish, Hindi, and German, letting your words flow in more places than ever. These voices are in beta—perfect for most uses but requiring extra validation for structured inputs like phone numbers.
Bigger, Better, Faster, Stronger Voice Engine 2.0
We are excited to announce significant updates to Voice Engine 2.0, enhancing reliability, scalability, and performance:
1. Enhanced Scalability: Voice Engine 2.0 supports larger-scale deployments effortlessly.
2. Improved Latency: Faster response times, especially in dynamic, interruptive conversations.
3. Reduced Crosstalk: Significant mitigation of overlapping or delayed agent responses during user interruptions.
4. Expanded SIP Trunking: Integrate with Telnyx and 3CX.
5. RAG: Voice Engine 2.0 supports Knowledge Bases.
We’ve changed how phone numbers are managed:
Voice Engine 2.0 assistants only use 2.0 numbers.
Voice Engine 1.0 assistants only use 1.0 numbers.
New agents default to Voice Engine 1.0 and imported Twilio numbers default to 1.0.
Additionally, we’ve made adjustments to ensure everything runs smoothly:
Advanced warm transfer features are only available in Voice Engine 1.0, but standard transfers remain fully functional.
Resolved double-call behavior by disabling the “Call Me” button during active test calls.
Fixed issues causing agents to repeat or stop speaking unexpectedly.
Improved handling of simultaneous call events to avoid errors.
Team Assistants now support multiple languages.
Fixed syncing issues with HubSpot during outbound calls.
Resolved problems with deleting unverified caller IDs.
Enterprise: Inbound Assistants can process custom variables in prompts.
Hire an Expert: Connect with Solution Partners for Same-Day Support
Need expert help? You can now request direct assistance through the “Hire an Expert” form in the Assistant View or here. Fill out the request, and one of our battle-tested Solution Partners will provide same-day support, helping you troubleshoot, optimize workflows, and get the most out of Synthflow.
Synthflow provides pricing guidelines to give you an understanding of the scope of services offered. However, final pricing is determined through direct negotiation between you and your selected Solution Partner, ensuring flexibility based on your specific needs.
PAYG Top-Up System
PAYG top-up system: We have introduced a top-up system for Pay-As-You-Go users.
Account Management: Cal.com for Subaccounts
Managing accounts and integrations just got easier with these new updates designed to streamline your workflow and boost efficiency.
Cal.com Integration: Subaccounts can now schedule tasks and manage Cal.com connections seamlessly.
Smarter Subaccount Tracking: Fixed discrepancies in subaccount counts for accurate reporting.
Navigation Updates: Streamlined access to subaccounts from Agency > Permissions.
API: Get & List Subaccounts, Widget, Knowledge Base
New API updates provide better data access and automation:
• Get & List Subaccounts: View usage data and activity details for individual or all subaccounts.
• Widget API & Webhook Support: Extract info from widgets programmatically for improved workflow automation.
• Knowledge Base: Manage knowledge bases via endpoints for creation, retrieval, and updates.
Flow Designer Closed Beta
Our next-generation conversational path tool is here—take full control of your AI-driven conversations. Request access via the form to join the closed beta.
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.
Get ready to design conversational paths with ease. Request access through this form!
Workflow Builder 2.0 and Batch Calling Deprecation
Batch calling has been retired and replaced by a fully automated experience in Workflow Builder.
New Workflow Templates: Explore an upgraded library of batch workflow templates, powered by the next-gen Workflow Builder for greater efficiency and flexibility.
Inbound to Spreadsheet
Make call from a form and update the spreadsheet (template link)
Batch calling (template link)
4 new automation steps for workflows:
Make a phone call to trigger the phone call.
Make a SIP Trunk call if you did bring your own voice provider.
Initiate a phone call and receive call data within 5 minutes, making it ideal for streamlining form qualification processes.
Receive a call and access the call data immediately afterward.
We really hope you enjoy these updates! As always, leave us feedback.
February 2nd, 2025
Big news...the Synthflow AI Voice Agents Marketplace is live! 🚀
Businesses need powerful AI templates, and yours could be the next big thing.
To celebrate, we’re running a Launch Contest with $500 cash, 1,000 free minutes, and a live session with Kevin from Synthflow AI up for grabs! 🏆
How to Win:
1️⃣ Submit your AI template before Feb 7, 23:59 ET.
2️⃣ Make sure it includes CRM actions, scheduling tools, or call automation (businesses love these!).
3️⃣ If you’re aiming for the Top Prize, fill out the interest form—this confirms you’re in for the live build session with Kevin.
The Rewards:
🥇 Top Template: $500 cash + 1,000 minutes + live session with Kevin.
🥈 Top 3 Templates: $300 cash + 1,000 minutes each.
🥉 Top 10 Templates: 500 minutes each.
Don’t miss your shot at cash, recognition, and marketplace exposure. Submit your template now!
How to Submit a Template:
Create Your Template: Make sure it addresses a real-world need.
Upload to Synthflow: List it on the Marketplace so users can access it quickly.
Watch the Tutorial: Follow the guide below to ensure a smooth submission.
For more details, check the Terms and Conditions. Questions? Reply to this email, we’ve got you.
December 19th, 2024
We’re excited to share the latest updates. Here’s what’s new:
Improved Interface for Actions and Test Calling: Enjoy clearer action organization (Before, During, After Call) and a relocated test console for a more focused workspace.
Templates for Industry-Specific Use Cases and Custom Actions: Explore them in the Templates section of your dashboard.
Advanced Language Settings: Voices from ElevenLabs can now be imported directly, with options to select the transcriber language and synthesizer model independently from the chosen voice.
More API Configurations: Configure agent timezones and initialize custom actions via API.
Help Center: Access support, sales, documentation, and the Synthflow Academy all in one convenient location.
Email Notifications for Errors: Workspace admins will now receive automatic error alerts, ensuring critical information is always at your fingertips.
Workflow Builder 2.0 and Batch Calling Deprecation: Batch calling is now retired and fully integrated into workflows for better automation. Workflows now offer seamless integration with assistants and new templates, including batch workflows built on our native workflow builder.
New Subaccount Concurrency Limits and Member Invitations: You can now configure concurrency limits for subaccounts, and subaccount members have the ability to invite others to join the workspace.
Fixes and Stability Enhancements: Enjoy improved stability with key bug fixes.
Templates for Industry-Specific Use Cases and Actions
We’re excited to introduce new templates to simplify agent setup across industries! Now available are templates for Mortgage Lead Qualifier, Mortgage Receptionist, Restaurant Concierge, Property Dormant Lead Qualification, Policy Renewal and Upselling, Healthcare Receptionist, and Insurance Customer Support. Additionally, we’ve added new templates for custom actions to seamlessly integrate with GoHighLevel and HubSpot. These ready-to-use templates are tailored to specific use cases, enabling faster setup and optimized engagement. Explore them in the Templates section of your dashboard today!
Enhanced Usability Across the Platform
We’ve made several improvements to refine the user experience.
New Action Placement
Now the actions are more structured, clearly showing which happen before, during, and after the call.
New Test Call Placement
We’ve moved the test console to the sidebar for a cleaner, more focused workspace. Find everything you need right where you expect it.
New Help Center
It is easier than ever to get help, with a single point of access to our support and sales teams, the help center, the API reference documentation, and the Academy!
Templates for Industry-Specific Use Cases and Custom Actions
We’re excited to introduce new templates to simplify agent setup across industries! Now available are templates for Mortgage Lead Qualifier, Mortgage Receptionist, Restaurant Concierge, Property Dormant Lead Qualification, Policy Renewal and Upselling, Healthcare Receptionist, and Insurance Customer Support. Additionally, we’ve added new templates for custom actions to seamlessly integrate with GoHighLevel and HubSpot. These ready-to-use templates are tailored to specific use cases, enabling faster setup and optimized engagement. Explore them in the Templates section of your dashboard today!
Advanced Language Settings
Options to select the transcriber language and synthesizer model independently from the chosen voice.
Import Any ElevenLabs Voice
Easily import any voice from ElevenLabs public library using it's voice ID.
More API Configurations
Our API just got more powerful. Agent timezones can now be configured using the new timezone parameter. Additionally, a new endpoint allows you to initialize custom actions directly via the API.
With updates to the GET Calls request, you can specify model IDs to retrieve assistant-specific calls, including executed actions and their return values. We’ve also made it easier to access widget embed URLs directly from the Get Assistant request.
Email Notifications for Errors
Workspace admins will now automatically receive email notifications for errors. This feature, enabled by default for all workspace admins, ensures that you never miss critical information affecting your workflows.
Workflow Builder 2.0 and Batch Calling Deprecation (Coming Soon)
Batch calling is being retired and fully integrated into workflows for better automation. Workflows will offer seamless integration with assistants and new templates, including batch workflows built on our native workflow builder.
New Subaccount Concurrency Limits and Member Invitations
You can now configure concurrency limits for subaccounts, and subaccount members can invite others to join the workspace. Additionally, when subaccounts are imported into Synthflow, they’ll automatically connect to GoHighLevel, streamlining setup processes for agencies.
Continuous Fixes and Stability Enhancements
We’ve addressed numerous bugs to ensure a smoother experience. Key fixes include resolving issues with cal.com scheduling, call transfer errors, playback failures, and assistant hang-ups due to long silences. Human availability errors that prevented call initiation have been fixed, along with improvements to Deepgram Spanish transcription.
The widget now supports Azure integration, bringing enhanced privacy and compliance for EU users. This addition makes deploying real-time AI solutions more secure and versatile.
Admins can now copy model and team IDs directly from the Assistants page for quicker access. Additionally, when subaccounts are imported into Synthflow, they’ll automatically connect to GHL, streamlining setup processes for agencies.
These updates reflect our ongoing commitment to improving Synthflow’s usability, stability, and compliance. As always, we value your feedback and look forward to hearing how these changes enhance your experience!
December 3rd, 2024
We’re excited to share the latest updates. Here’s what’s new:
Privacy & Compliance: Top-tier security for your data with SOC 2 and HIPAA certifications.
Azure OpenAI Service Integration: Process data in the EU with added privacy features 🌟
Enhanced Usability: Faster Prompt Editing and Improved Call Exporting 💡
New Learning Opportunities: Special course for Agencies & new tutorials 📚
Smarter Rate Limit for Enterprise Customers: requests exceeding the quota will be queued and automatically processed 📈
Check out these and other performance improvements to make Synthflow better than ever!
Enterprise-Grade Security and Protection
With airtight internal security, your data is safe with us:
SOC 2 Certification: Guaranteed industry-leading data security and privacy protection
HIPAA Certification: Safely manage sensitive patient data for healthcare and beyond
GDPR Compliance: Deploy AI agents worldwide, fully compliant with EU data privacy laws
Bring Your Own Azure
We’re introducing an Azure integration designed with privacy and GDPR compliance in mind. You can now use LLMs from Azure OpenAI Service with data processing in the EU.
New Opt-out Toggle for Transcript & Recordings
Fully control which calls are transcribed and recorded. Never store sensitive information.
Improved Prompt Editing
Experience faster, more efficient editing with our updated prompt editor.
View and Export Call Logs
You can now view all call logs and export up to 10,000 of them for further analysis.
New Agency Course in the Synthflow Academy
Are you interested in our agency product? Our new Academy course will teach you everything you need to know about running your own agency through Synthflow. Enroll in the course today to learn about pricing plans, payments, workflows, custom domains, permissions, sub-accounts, embeddings, and more.
Rate Limit Queue for Enterprise Customers
Enterprise customers exceeding their outbound call rate limit will now benefit from a more seamless experience. Instead of receiving an error, requests exceeding the quota will be queued and automatically processed later.
Voice Engine 2.0 Updates
Voice Engine 2.0 has been upgraded with several enhancements to improve call quality and reliability:
Crosstalk Handling: Enhanced detection and management of overlapping speech for clearer conversations.
Voicemail Detection: Improved accuracy in identifying voicemail recordings.
Goodbye Detection: Smarter recognition of call endings for smoother transitions.
Greeting Improvements: Refined greeting logic for more natural and robust interactions.
Get Better, Faster, Stronger Support
Get holistic help from our excellent Customer Success team — now powered by Zendesk.
Try Our Embeddable Widget With Actions and OpenAI Realtime
If you haven’t already, check out the recording of the live launch to see the Widget in action.
The widget now also supports custom voices when you choose Real-Time Voice from OpenAI.
These updates aim to enhance user experience, improve privacy compliance, and provide greater flexibility across the platform. We look forward to hearing your feedback as you explore these new features!