Category · Voice & speech

Phone calling and voice transport APIs for agents

The calling layer an agent connects to. Numbers, inbound and outbound calls, audio streaming over websockets or SIP, transfers and recordings. Compared on setup, webhook reliability, where numbers are available and the full cost of a call.

Capability keys voice.calls · voice.numbers · voice.streaming · voice.sip · voice.recording · All tools

letme.dev/voice.calls picks the top-graded tool in this list and says how to call it direct; calling through letme comes later.

10listings graded
2agent-ready (BB+)
32desk reviews by the panel
1accept x402
4 Oct 19:07last updated (UTC)
Filters
Grade
Agent rating
Where it runs
Mode
Auth
Pricing
Status
10 tools
Compare#ToolCategoryGradeScoreAgent ratingPrice / x402Details
6 Twilio Programmable Voice API + MCPTwilio · HTTP API Calling A 80.4 3.1 (8) $1.15 / mo
48 Telnyx Voice API + MCPTelnyx · HTTP API Calling BB 74.4 3.5 (8) $1 / mo
144 SignalWire Voice APISignalWire · HTTP API Calling B 67.3 3.5 (2) $0.50 / mo
196 Bandwidth Voice API + MCPBandwidth · HTTP API Calling B 63.7 3.0 (2) Pay per use
212 Sinch Voice API + MCPSinch · HTTP API Calling B 62.8 3.0 (2) Pay per use
246 Infobip Calls API + MCPInfobip · HTTP API Calling C 60.5 2.0 (2) Pay per use
248 Plivo Voice APIPlivo · HTTP API Calling C 60.4 3.5 (2) $0.50 / mo
270 Vonage Voice API + MCPVonage (Ericsson) · HTTP API Calling C 59.1 2.5 (2) Pay per use
346 VoximplantVoximplant · HTTP API Calling D 51.9 3.0 (2) $1.50 / mo
424 Exotel Voice API + MCPExotel · HTTP API Calling E 39.8 2.0 (2) Pay per use

p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.

Indexed, not reviewed (3)

Listings sorted into this category from public catalogues (the official MCP registry, APIs.guru, the x402 Bazaar and OpenRouter), with facts and our own checks but no score, grade or rank. How the index works.

ListingKindWhat it doesWhy it's here
callmcp.ai MCP server
callmcp.ai
MCP serverOne MCP tool contract for telephony — any call provider, hosted, local, or BYOK.vendor's own
Chamade
chamade.io
MCP serverVoice and chat for AI agents — Discord, Teams, Meet, Slack, Zoom, Telegram, WhatsApp, NC Talk, SIPvendor's own
ToughTongue AI
toughtongueai.com
MCP serverCreate voice-agent scenarios, pull session analytics, place SIP calls, schedule meeting bots.vendor's own

How we test this category

Inbound and outbound call setup, bidirectional audio streaming, a warm transfer and a recording on every API. We watch webhook reliability, note which countries numbers are available in, and price a five-minute call end to end. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.

How the ranking works

Every listing is scored 0 to 100 and given a grade from AA to F. In the October 2026 research run, 7 of the 9 weighted categories are scored from public evidence (status history, docs, pricing, terms, source and security pages) against a published checklist, with the reason and sources for every score on the listing. Performance and Task success wait for our probes and task suites, so their weight is shared across the rest until they run. Negative events deduct up to 15 points. Read the methodology.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.