Posts by Abhishek Kumar
Twilio Elastic SIP Trunking for AI Voice Agents: Setup Guide
How to set up Twilio Elastic SIP Trunking for an AI voice agent. Create the trunk, point Origination at Dograh, allow Dograh's IP on Termination, move your numbers, route them to the agent and test, plus what a production trunk still needs.
Speech-to-Text API in Python: Streaming a Phone Call
Stream a phone call to a speech-to-text API in Python, sending 8 kHz mu-law audio over a WebSocket with the settings that matter for phone audio, partial transcripts, a recorded call paced as live, then a Twilio Media Stream.
ElevenLabs Scribe Speech-to-Text for Voice Agents on Phone Calls
ElevenLabs Scribe for voice agents, covering the batch and realtime models, how Scribe v2 Realtime handles 8 kHz phone audio, its latency, accuracy, languages and price, how it compares with Deepgram, and how it runs in Dograh.
Cold Calling Practice With AI: Build a Roleplay Caller
Build an AI practice prospect for cold calling from a persona prompt with real objections and a fixed pickup line, call it from the browser and a phone, grade the rep with a QA rubric, and review each recording and transcript.
Open-Source Predictive Dialer With an AI Agent: The Handoff
How an open-source predictive dialer and an AI voice agent split the work, with VICIdial pacing the calls and Dograh taking the answered ones over Asterisk ARI and writing outcomes and do-not-call requests back, plus the two-second abandoned-call rule.
Voice Activity Detection in Python: A Working Example
Voice activity detection in Python with Silero VAD on a real 8 kHz phone call. Install it, find speech segments, change one setting at a time, then stream it in 32 ms chunks the way a live voice agent does.
Open-Source VAD Models Compared for Phone Agents
A comparison of Silero, WebRTC VAD, TEN VAD, FireRedVAD, NVIDIA MarbleNet, pyannote and FunASR, seven open-source VAD models for voice agents, on licence terms, sample rate, size and whose benchmark says what.
Securing Tool Calls and Webhooks in Voice Agents: What to Check
How to secure the HTTP requests a voice agent makes mid-call and the webhook it sends after, with a stored credential on every request, one narrow job per endpoint, a timeout that fails closed, safe webhook receivers and the log line to keep.
Running Voice AI on Your Own GPUs: Sizing, Serving and the Monthly Bill
How to run a voice agent's models on your own GPUs, covering memory per model, serving the language model with vLLM and speech with Speaches, how many calls a card carries, and what an always-on GPU costs each month.
Pipecat Flows Explained: Nodes, Functions and a Working Example
How Pipecat Flows splits a voice agent call into nodes and functions, with a small YAML and Python example, the cascade-only limit, and how a visual workflow builder such as Dograh's maps to the same idea.
Managing Multiple Clients on One Voice AI Platform
Managing multiple clients on one voice AI platform: one organization per client or one for all, and how to keep each client's numbers, prompts, knowledge files, model keys, reports and billing apart on Dograh Cloud or self-hosted.
Voice AI Agency Tech Stack: Telephony, Models and Platform
The voice AI agency tech stack layer by layer: carriers and SIP trunks, speech-to-text, the language model, the voice and the platform, with model costs per minute kept apart from the platform and one example stack per budget.
LiveKit VAD vs Pipecat VAD: Every Setting and Its Default
LiveKit VAD and Pipecat VAD settings compared from each repo: the Silero thresholds, start and silence timers, turn and interruption options, and what to change for noisy phone lines.
WebRTC VAD vs Silero VAD: Which Works on Phone Calls
WebRTC VAD vs Silero VAD for voice agents: how each detects speech, where each fails on noisy 8 kHz phone audio, the published accuracy numbers and which one voice agent stacks ship.
STIR/SHAKEN and Caller ID: Why AI Calls Get Marked as Spam
Why AI calls get labelled Spam Likely: what STIR/SHAKEN attestation levels A, B and C mean, why platform calls with outside numbers get B, why signed calls still get labelled, the Free Caller Registry, branded caller ID, how Dograh picks caller IDs and how to recover a flagged number.
How to Migrate From ElevenLabs Agents to Open-Source Voice AI
How to migrate from ElevenLabs Agents to open-source voice AI without losing the voice: export the agent, move the voice on your own key, rebuild the prompt and flow, map each tool, move the knowledge base and switch numbers one at a time.
Red-Teaming a Voice Agent Before Launch: A Test Script
Red-teaming a voice agent before launch: 50 hostile test lines in four sets with the safe answer for each, run in Test Chat, then on a real phone call, scored with QA and traces, and fixed with limits.
API Key Safety for Voice AI: BYOK, Rotation and Service Keys
API key safety for voice AI: where model, telephony and Dograh keys live in a self-hosted stack, how to rotate each kind without dropping calls, how service keys work, and what to do after a leak.
Voice Activity Detection Explained: VAD for Voice Agents
Voice activity detection explained for voice agents: how VAD scores call audio, why it is not end-of-turn detection, the four ways phone lines trip it up, and the setting that fixes each symptom.
Speechify API for Voice Agents: What It Can and Can't Do
Does Speechify's API hold up on a live phone call? Its voices, streaming, phone audio formats, speed and limits, checked against Speechify's docs, and how Dograh runs Simba 3.2 and 3.0.
AI Collection Calls: How AI Agents Handle Debt Collection Calls
One AI debt collection call, line by line: the fixed opening, the identity check, the collector notice, the agreed payment and the moment a person takes over.
AI Voice Agents for Debt Collection in Fintech: Campaigns at Scale
How app lenders run early collections calls at volume: one campaign per delinquency stage, retries and pacing you control, and every result sent back to the loan system after the call.
Voice Cloning for AI Voice Agents: The Complete Guide
When a cloned voice helps a phone agent and when it backfires, what the person you clone has to agree to, how to judge a clone on phone audio, and which open models can clone.
Deploying an AI Voice Agent to Production, Step by Step
A go-live checklist for an AI voice agent: a real phone test, phone numbers, concurrency limits, monitoring, a pinned version and a way to back out.
The Voice AI Cookbook: Five Ready Call Flows for Common Use Cases
Five copy-ready voice agent call flows, booking, reminder, intake, survey and transfer, with the nodes, tools and settings for each one in order.
Voice Agent Testing and Evaluation: How to Benchmark Before Launch
How to know a voice agent is ready with numbers: a fixed scenario set, several runs per leg, per-step QA scores and the same tests on every new version.
Voice AI Security: Threats and Safeguards for Phone Agents
What callers try to make an AI phone agent do, from prompt tricks to posing as someone else, and the safeguards that stop each one.
VibeVoice for Voice Agents: Long-Form Voice, Not a Phone Line
What Microsoft's VibeVoice models are built for, what their license and Microsoft's own card say about commercial use, how the realtime model fits a live call and what to run instead.
Orpheus TTS for Voice Agents: What Emotion Tags Cost in Speed
What Orpheus 3B's emotion tags do on a call, how it scored in our benchmark, what a 3B voice costs to serve, its license and how it runs behind Dograh.
Qwen3-TTS for Voice Agents: Ten Languages, Tested in English
What Qwen3-TTS offers a voice agent: ten languages, preset voices and three-second cloning, our English benchmark result, how to serve it and how it runs behind Dograh.
Nvidia Parakeet for Voice Agents: v2 or v3 Beside Your LLM
Nvidia Parakeet TDT 0.6B for phone agents: why it fits beside your language model on one GPU, v2 for English against v3 for 25 languages, what streaming means for each, serving it for Dograh, and CC-BY-4.0.
Open-Source Speech-to-Text Models in 2026: A Voice Agent Guide
How to pick an open-source speech-to-text model for a phone agent: streaming or one sentence at a time, accuracy on phone audio, languages, licences and what fits beside your LLM on one GPU.
The Ultimate Guide to Voice AI for Developers: API to Release
A developer's map of a phone agent: the call pipeline, the three points where your code joins a call, the API, SDKs and MCP, traces, testing, security and the release.
AI Voice Agents for OTP and Identity Verification Callbacks
How a bank or fintech can use an AI voice agent for login and transaction confirmation callbacks: confirm the event with a yes or no, keep possession proof in the app, and what a spoken code costs when a flow still requires one.
How to Build an AI Cold Calling Agent in Dograh, Step by Step
A step-by-step build of an AI cold calling agent in Dograh: a fixed greeting with your business name, an opt-out path that ends the call and reaches your own list, a voicemail choice, a transfer to a rep and a campaign with calling hours.
How to Reduce Robotic TTS in Voice Agents: Fix the Words First
Why voice agents sound robotic and how to fix it: write text for the ear, spell hard names the way they sound, set the speed, pick the voice and test it on a real phone call.
How to Scale to Thousands of Simultaneous Calls With Voice Agents
Scaling a voice agent to thousands of simultaneous calls means raising a chain of limits in order: the platform and campaign limits, the carrier's calls per second, speech and model provider rate limits, and your servers, each proven with a load test.
Observability for Voice AI: Metrics That Predict Call Quality
Which signals to watch across many voice agent calls to spot bad ones early: latency per layer as median and slowest turn, interruptions, silence, provider errors and transfer-rate changes, and where each lands in Dograh.
STT and TTS Concurrency Limits: When Several API Keys Help
Where speech-to-text and text-to-speech vendors count concurrency, what several API keys on one Dograh connection do, when separate keys add capacity, how to turn a limit into a call count, and when to ask the vendor instead.
How to Run Kokoro TTS Locally for a Phone Voice Agent
A step-by-step tutorial to run Kokoro TTS on your own GPU with Kokoro-FastAPI inside Dograh's Docker setup, set the model, voice and speed fields, and prove the voice with a browser call and a phone call.
How to Run Faster-Whisper Locally for a Voice Agent With Speaches
A step-by-step tutorial to run faster-whisper on your own GPU with Speaches, inside Dograh's Docker setup, connect it as the agent's speech-to-text, pick a model size for phone audio and prove it with a test call.
HIPAA-Compliant Voice AI for Medical Billing Calls
How to run patient billing and balance calls with a voice agent under HIPAA and the TCPA: verify the patient before any amount is spoken, get consent for outbound balance calls, keep voicemails plain and take payment by link or payment line, never by voice.
HIPAA-Compliant Voice AI for Dental Clinics: Front Desk Privacy
How a dental practice runs reception, recall and balance calls with a voice agent under HIPAA: what each call type may say before and after verification, where recall calls turn into marketing, and how a small practice keeps every copy of a call on one server.
HIPAA-Compliant Voice AI for Telehealth: The Calls Around the Visit
How to run telehealth booking, reminder and tech-check calls with a voice agent under HIPAA: what each call may say before and after verification, how the join link stays off the call, where each copy is stored and who else hears the call.
Which Parts of a Voice AI Stack Need a BAA
A layer-by-layer guide to business associate agreements for healthcare voice AI: the carrier, the platform, speech, language and voice models, hosting, traces and tools, across hosted and self-hosted setups.
Verifying Patient Identity Before a Voice Agent Shares PHI
How to build patient identity verification into a healthcare voice agent: keep the record out of the agent, check answers against your own system, and handle failed checks and family callers.
What Counts as PHI on a Voice Agent Call
Which parts of a voice agent call count as PHI, from the live audio and the caller's number to recordings, transcripts, logs and traces, and where each copy lives in a self-hosted install.
HIPAA-Compliant Voice AI: What Self-Hosting Changes
What self-hosting changes for HIPAA-compliant voice AI: which call data stays on your servers, which vendors still hear the call and need a BAA, and which safeguards stay with your team.
How to Add Tool Calls to a Voice Agent (CRM, Calendar, Webhooks)
A step-by-step guide to adding tool calls to a voice agent with an HTTP API tool: setup, parameters, the timeout, the lines the caller hears while a lookup runs, and how the agent handles a failed request, shown in Dograh.
Designing Conversation Flows With a Visual Drag-and-Drop Builder
How a visual drag-and-drop builder turns a phone call into nodes, edges, conditions and variables, with every node type, pathway field and variable rule shown in Dograh's workflow builder.
From Fork to Production: Contributing to Open-Source Voice AI
A step-by-step guide to forking an open-source voice AI platform, running the full stack locally, sending changes upstream, and running your own fork in production, with Dograh as the worked example.
How to Self-Host a Voice AI Agent With Docker
A step-by-step tutorial to self-host Dograh with Docker: what you need, the start script and what it writes, creating an account and a first agent, a browser test call, and the defaults to close before real callers.
Air-Gapped Voice Agents: AI Calling With Zero Data Egress
What stays inside and what still needs the network when you run a voice agent air-gapped: every connection a default Dograh install makes and how to switch it off, local models, the carrier at your own PBX, and records.
Pre-Call Data Fetch: Personalizing Calls With CRM Context
How to set up Pre-Call Data Fetch in Dograh: turn it on in the Start Call node, answer the request from your CRM endpoint, use the values in the greeting and prompts, test in the browser and change models for one call.
How to Extract Structured Data From Calls Into Any CRM
How to pull typed fields and one outcome from every voice agent call in Dograh and send them to your CRM: choose the fields, turn on extraction on the right node, add call dispositions, send a webhook and check values against the transcript.
How to Add a Voice Widget to Your Website, Safely
A step-by-step guide to putting a published Dograh voice agent on your website: turn on embedding, set Allowed Domains, choose the widget type and look, paste one script tag and pass page details safely.
Knowledge-Base Grounding: How a Voice Agent Answers From Files
How knowledge-base grounding works in a Dograh voice agent: how retrieval finds an answer, which file types and modes to use, how to keep answers to your documents and how to test with real caller questions.
Telephony 101 for Voice AI: Numbers, Carriers and SIP Trunks
A beginner's guide to the phone side of a voice agent: what a telephony provider does, a provider account versus your own SIP trunk, what Twilio, Telnyx and Plivo charge, which providers connect to Dograh and which of them can transfer a call to a person.
How to Choose an LLM for Voice Agents: Test the Tool Calls First
How to choose a language model for a voice agent: test tool calls made from spoken input first, then reply speed on a real phone call, then cost per call, and decide between hosted models and open weights, with the models Dograh can run.
How AI Voice Agents Handle Accents and Background Noise
Why accents and background noise still break voice agents, and the fixes in order: speech-to-text chosen on your own callers' audio, a short dictionary, interruption settings that ignore noise, prompt rules for misheard words, and testing on real phone calls.
Spinning Up a Voice Agent From Claude Code or Codex via MCP
A step-by-step tutorial: connect Claude Code or Codex to Dograh's MCP server, describe a voice agent in plain words, approve the plan, let Dograh check each save, publish drafts in the app, then improve the prompt from real call transcripts.
How to Add MCP Support to a Voice Agent, Step by Step
A step-by-step tutorial for connecting an MCP server to a Dograh voice agent: the credential, the MCP Server tool, the Tools Filter, ticking tools on a step, prompting when to call them, testing on a real call and planning for a slow or missing server.
How to Migrate From PolyAI to Open-Source Voice AI: Step by Step
How to migrate from PolyAI to open-source voice AI: pull the agent with PolyAI's ADK, map each file to Dograh, rebuild the flow, move Python functions to HTTP API tools, retest on your new model and move one number at a time.
How to Build a Voice Agent for Banking in Dograh, Step by Step
A step-by-step build of an inbound member service voice agent for a bank or credit union in Dograh: greeting and lookup, document answers, verification through the bank's system, balance tools after the check, fraud and lost-card hand-offs, webhooks and phone tests.
Data Residency for Voice AI: A Buyer's Checklist of Every Setting
A buyer's checklist for data residency in voice AI: every place a call's data goes, from servers and models to the phone carrier, telemetry, the quickstart tunnel, tracing, tools and remote access, with the setting that keeps each one in your region.
How to Pass a SOC 2 Review With a Self-Hosted Voice Agent
How a self-hosted voice agent fits a SOC 2 review: why it sits inside your own system boundary, where its call data lives, the defaults to close before an audit, the change evidence it keeps, and which outside vendors still need review.
On-Prem Voice AI for BPOs: Keep Each Client's Calls In-House
What on-prem voice AI means for a BPO: every place a client's call goes, why client contracts decide it, the platform and model layers, sizing servers for many programs, the phone path with transfers, and what the BPO takes on.
On-Prem Voice AI for Accounting Firms: Count Who Hears the Call
Where a tax firm's voice agent calls go and what each place means under the FTC Safeguards Rule and IRC 7216: hosted providers the firm must oversee, consent for providers outside the US, what full on-prem takes with self-hosted Dograh and open-weight models, and when it is not worth it.
How to Migrate From Voiceflow to Open-Source Voice AI: Step by Step
How to migrate a Voiceflow phone agent to open-source voice AI: export the environment through Voiceflow's API, map playbooks, workflows and tools to Dograh, move Code and Function logic to an endpoint, test on a real phone line and move numbers one at a time.
How to Migrate From Synthflow to Open-Source Voice AI: Step by Step
How to move off Synthflow onto open-source Dograh: export each agent version, save what the export leaves out, map every Flow Designer node, re-create actions and transfers, test on a spare number and move one number at a time.
How to Build a Voice Agent for Veterinary Clinics in Dograh
A step-by-step Dograh build of a vet clinic front-desk voice agent: a greeting with the emergency line, clinic details at call start, an owner check, booking from live slots, refill requests with a fixed closing line, an on-call transfer and a webhook, tested in the browser and on a real phone.
How to Build a Voice Agent for Insurance: A Policy Service Agent
A step-by-step Dograh build of an inbound policy-service agent for an insurance agency: caller lookup without policy data, verification before any detail, change requests written back, a fixed hand-off line into Transfer Call for licensed questions, a webhook to the agency system and a real phone test.
HIPAA-Compliant Voice AI for Pharmacy: The BAA Is Half the Job
What HIPAA asks of a pharmacy voice agent: which vendors on a call are business associates and need a BAA, three ways to set the agent up, why a BAA does not stop a medicine being named before verification, and where recordings, transcripts and traces live.
Building an Auditable Voice AI Stack for Security Reviews
How to build a voice AI stack a security reviewer can audit: step-tagged transcripts, tool calls, the agent version and model settings behind every call, access logs for who opened the records, and QA sampling, mapped to NIST SP 800-53.
How to Migrate From Bland AI to Open-Source Voice AI: Step by Step
A step-by-step migration from Bland AI to Dograh: export pathways, numbers and knowledge bases through Bland's API, choose a new model layer, rebuild each pathway, test on a spare number, then move one number at a time.
On-Prem Voice AI for Law Firms: Every Place an Intake Call Goes
What a law firm has to run on its own servers so a privileged intake call reaches no outside company: the voice platform, speech and language models, recordings and transcripts, and the phone path, plus when on-prem is not worth it.
How to Build a Voice Agent for Law Firms in Dograh, Step by Step
A step-by-step Dograh build of a law firm intake and booking agent: names before facts, a conflict lookup with a stop path, a fixed no-advice line, a booking tool that cannot double-book, a transfer, a webhook and a phone test.
How to Build a Voice Agent for E-commerce With Shopify Returns
A step-by-step build of a returns voice agent for a Shopify store in Dograh: Pre-Call Data Fetch, a verify step, the return policy in the Knowledge Base, HTTP API tools for the store's eligibility check and a retry-safe return request, a handover and a webhook, tested on a real phone line.
How to Build a Voice Agent for Hotels: A Reservations Agent in Dograh
A step-by-step build of an inbound hotel reservations agent in Dograh for callers with no record: FAQ answers, live rooms and rates, a read-back, the booking and a payment link from the hotel's own system.
How to Build a Voice Agent for Restaurants: Phone Orders to the POS
A step-by-step build of a phone-ordering agent in Dograh: menu in the Knowledge Base, prices from the POS, a full read-back, and an order confirmed only when the POS accepts it.
How to Build a Voice Agent for Automotive Dealerships That Never Double-Books
A step-by-step build of a dealership service-booking agent in Dograh: recognise the customer, verify the owner, offer live slots by job type and book them so a retry never double-books a bay.
How to Build a Voice Agent for Real Estate: Qualify, Then Book
A step-by-step build of an inbound lead-qualification and viewing agent in Dograh: load the listing from the dialled number, ask every caller the same questions, write the lead to your CRM and book a viewing.
How to Build a Voice Agent for Healthcare: A Patient Booking Agent in Dograh
A step-by-step build of an inbound patient booking agent in Dograh: find the patient, verify before any health detail, book live slots and write the call record back.
HIPAA-Compliant Voice AI for Hospitals: Count the Vendors That Hear the Call
What HIPAA asks of a hospital voice agent: where PHI lands on a call, which vendors need a BAA, the minimum necessary rule, access controls and audit logs, and what self-hosting changes in the chain.
On-Prem Voice AI for Logistics: When Your Own Servers Earn Their Keep
What on-prem voice AI means for a logistics operation: which call data is at stake, the GPU and server sizing, who owns uptime, and when on-prem beats self-hosting in your own cloud.
How to Build a Voice Agent for Logistics: An Order-Status Agent in Dograh
A step-by-step build of an inbound shipment-status voice agent in Dograh: Pre-Call Data Fetch, identity verification, an HTTP API tool on live tracking data, tool Messages and a webhook to the CRM.
How to Migrate From Retell AI to Open-Source Voice AI: Step by Step
A step-by-step move from Retell AI to Dograh: read agents from Retell's API, rebuild the flow, re-point webhooks, test, then take numbers off Retell's trunk.
How the Voice AI Pipeline Works: STT to LLM to TTS, Step by Step
Follow one caller's sentence through speech-to-text, the language model and text-to-speech, with where the time goes at each stage and what breaks between them.
What Is an Orchestration Layer in Voice AI? Every Job It Runs
What a voice AI orchestration layer does on a live call, from custom dictionaries and turn detection to transfers, voicemail and speech-to-speech models.
Barge-In, Endpointing, and Turn-Taking: Voice UX Fundamentals
How a voice agent decides the caller is done, when to stop talking, and which sounds to ignore, with the settings that control each decision.
Cascade vs Speech-to-Speech: Tradeoffs Explained
How cascade and speech-to-speech voice agents compare on tool calling, latency, voice and cost in 2026 benchmarks, and how to choose per agent.
How to Migrate From Vapi to Open-Source Voice AI: Step by Step
A step-by-step move from Vapi to Dograh: export assistants, rebuild the flow, re-point webhooks, test on a spare number, then move phone numbers one at a time.
How to Build an AI Receptionist: Set Up a Voice Agent in Dograh
Build an AI receptionist in Dograh, step by step: a hair salon greeting, an FAQ knowledge base, booking through an HTTP tool and a transfer you test by phone.
Testing Voice Agents Before You Go Live: Five Tests, in Order
Five tests to run before a voice agent takes real calls: a web call, simulated callers, repeat runs per leg, a real phone call and a small load test.
Automated QA for Voice Agents: Grade the Agent, Not the Caller
What Dograh's QA node checks after each call, and why a 5-10% sample of live calls is enough to find common failures within days.
Prompt and Flow Design Patterns for Reliable Voice Agents: Split by Guarantee
Where to split a voice agent's call into nodes, where exact wording comes from, and how to prove each leg holds up over repeated runs.
How to Read Call Traces to Debug a Voice Agent: Find the Layer
Open one bad call's trace, find the first layer that went wrong, and replay that step several times before you change the prompt.
Webhook-Driven Voice Agents: Real-Time Data In and Out
How webhook-driven voice agents move call data in and out: what Dograh sends after a call, how to avoid duplicates and how to catch results that never arrive.
Automating Voice Workflows With n8n and Webhooks
How to automate voice workflows with n8n and webhooks: start calls from any trigger, sync every call result, and answer the agent mid-call without dead air.
Booking Calendly Meetings Mid-Call With a Voice Agent
How to book Calendly meetings during a live voice agent call: the two requests, the details Calendly needs, and what to do when a slot is taken first.
API Triggers: Start a Voice Agent Call From Any System
How API triggers let you start a voice agent call from any system: the request, the reply, what to put in initial_context and the consent check up front.
Integrating Voice Agents With Your Stack: The Complete Guide
How to connect a voice agent to your CRM, calendar and workflow tools. Integrating voice agents with your stack, from starting calls to syncing every result.
How to Build a Voice Agent on Fully Local Open-Source Models
The build side of running voice AI locally: what fits on one 24GB card, which runtime to use per stage, and what the latency actually looks like on a phone call.
What 1 Million AI Voice Calls Reveal for Restaurants and Home Services
Yelp Host passed a million calls and the announcement describes how they sound. What decides whether a phone agent holds up unsupervised is somewhere else.
AI Voice Agents for Law Firm Intake: Privilege Starts at Hello
Why a caller is confidential before the firm agrees to anything, and how that decides where an intake voice agent is allowed to run.
AI Voice Agents for Debt Collection: Verify First, Then Talk
Why right-party verification is the first legal gate on a collections call, and what Regulation F requires of an automated dialer.