Check an owned number before enabling agent voice
Verify number ownership, Telnyx routing, allowed peers and voice admission before planning an agent conversation.
Lupin field guides
Voice
Voice architecture, conversational timing and telephony operations.
20 published articles
Choose SIP and WebSocket diagnostics by the active transport
Separate telephony signaling, gateway media and provider sessions before diagnosing configuration or migration problems.
Compare Flash and Multilingual with the current synthesis path
Read captured synthesis configuration and compare provider model trade-offs without replacing the workspace agent’s identity.
Debug interruptions that leave an agent speaking over callers
Trace speech onset, playback cancellation, response fencing and interrupted context as separate failure points.
Diagnose voice media failures by connection phase
Separate carrier answer, media authorization, provider sockets and output playback before retrying a paid call.
Distinguish a requested hangup from a confirmed call end
Handle asynchronous closure, terminal events and reconciliation without releasing capacity before the provider confirms termination.
Full duplex audio does not identify the conversation model
Separate simultaneous audio transport from transcription, response generation, interruption handling and model identity.
Keep voice tools behind authenticated workspace approvals
Separate caller identity, conversational intent, private tool access and exact approval in a voice-capable agent.
Make language switching explicit in a voice conversation
Separate language preference, recognition hints, voice compatibility and authorization during multilingual phone conversations.
Measure voice latency without adding overlapping clocks
Separate admission, carrier setup, conversation response and workspace tools while accounting for warm connections and missing data.
Normalize spoken text without changing the approved facts
Improve spoken phrasing while preserving exact action arguments, names and source meaning.
Operate voice transcripts with deliberate retention
Separate recordings, signed transcripts, operational timings and workspace content policy when investigating calls.
Plan a migration from cascading voice to native audio
Preserve phone identity and approvals while comparing media contracts, diagnostics and rollback for a native audio transition.
Plan voice work around duration and budget guards
Distinguish maximum duration, monthly allowance, active-call concurrency and verified spending ceilings.
Prepare an outbound callback for exact human approval
Read admission status, bind the purpose and destination, and preserve one approved dial attempt through retries.
Read transcript timing without confusing it with turn completion
Locate the boundary between recognized words and a completed caller turn before tuning voice latency.
Test voice behavior without dialing a real phone
Build synthetic fixtures for framing, endpointing, interruption, signatures and authority before an operator runs a controlled phone trial.
Treat phone calls and SMS as separate agent capabilities
Map messaging profiles, voice connections, permissions and asynchronous outcomes before sharing a number between workflows.
Understand Scribe v2 Realtime in a phone audio pipeline
Follow audio formatting, partial text, manual commits and recognizer preparation without attributing the entire agent to ASR.
Verify voice webhooks before updating call history
Understand signature checks, replay windows and call binding across Telnyx events and ElevenLabs transcripts.