46elks Voice API vs Sinch Voice API + MCP

46elks Voice API 12

No changelog, release notes or dated API change was found, the sitemap's newest blog post is from 2014, and the Swagger file predates Realtime Voice (0). No dated changes in the 90 days from 8 August (0). Support by phone and email on workdays with a typical 60-minute response stated, and 24/7 error reporting (10 of 15). No official SDK (0). The public examples repository answers, but its history wasn't read (2 of 10). 0+0+10+0+2 = 12.

Sinch Voice API + MCP 79

Java SDK 2.4.0 (28 October 2026) adds Voice v2 helpers, Node 1.7.0 (15 October) and Python 2.3.0 (14 October) changed Voice v2, and the MCP server's 0.0.1-beta.7 (30 October) moved its voice tools to Voice API v2 (30). In the 90 days, Node 1.6.0 (23 September) and Python 2.2.0 (21 September) added Voice v2, Java 2.3.0 (15 October) did the same, and Java 2.2.0, .NET 1.5.1 (2 September) and the 28 October releases followed (20). v1 voice release notes stop in October 2022 and v2 has an undated what's-new page, while the SDK changelogs are dated (5 of 15). Official SDKs in four languages, with Voice v2 in Node, Python and Java (15). CI on the SDK repositories, with CodeQL and dependency review on Java and an audit job on Node (9 of 10). 30 + 20 + 5 + 15 + 9 = 79.

46elks Voice API 51

Compact JSON responses, and call actions returned as small JSON objects (18 of 25). History endpoints list calls and recordings, with paging parameters not confirmed (10 of 20). Errors carry error and detail (12 of 20). No idempotency key on POST /calls or number allocation (3 of 20). Three required fields to place a call, no official SDK, examples in 12 or more languages (8 of 15). 18+10+12+3+8 = 51.

Sinch Voice API + MCP 81

v2 lists take page_size, with no field selection (15 of 25). The v2 call list pages by link and filters by from, to, call type, time range, result and reason (18 of 20). v1 error reference with codes, and v2 errors carry a type and instance per the SDKs (15 of 20). v2 call, batch and service writes take an Idempotency-Key that returns the cached response for repeats within 10 minutes, and the webhook guide says to deduplicate on ce-id and ce-source (18 of 20). Official SDKs in Node, Python, Java and .NET, but a v2 dial is a nested commands document rather than a few fields (15). 15 + 18 + 15 + 18 + 15 = 81.

46elks Voice API 66

A Swagger 2.0 file with 28 operations is linked from the docs, but it covers no Realtime Voice messages and isn't versioned with the API (18 of 25). An llms.txt written for agents, with a task-to-endpoint table and webhook payloads, while docs pages are HTML (10). Each docs page explains parameters and when webhooks fire, such as voice_start loading only once a call connects (14 of 20). Form-encoded parameters with types in the Swagger file and few enums (9 of 15). Examples in many languages and a JSON error shape, with no error list (10 of 15). The /a1/ path, with no changelog found (5 of 15). 18+10+14+9+10+5 = 66.

Sinch Voice API + MCP 85

The v2 reference links an OpenAPI 3.1.1 file (version 2.0.59), read on 2 November with 11 paths and 17 operations (25). llms.txt with Markdown pages for v1 and v2 (10). Reference pages describe each SVAML action or v2 command, with a migration page on why to move to v2 (12 of 20). Typed fields with enums for call type, result and reason, and bounded integers such as maxCps and ttlSeconds (13 of 15). A v1 error and troubleshooting reference, request examples, and problem-details error answers (400, 401, 403, 404, 429, 500) documented on the v2 operations (15). Two API generations, v1 release notes last updated 2022-10-06 and an undated v2 what's-new page (10 of 15). 25 + 10 + 12 + 13 + 15 + 10 = 85.

46elks Voice API 40

HTTP Basic credentials per account, with separate credentials per subaccount and no scopes found (18 of 30). Subaccounts separate traffic, with no read-only credential or confirmation for paid actions (6 of 20). Callers' speech, DTMF and SMS replies reach the agent as untrusted input. The docs show how to verify callback origin, with no prompt-injection guidance (5 of 15). Call, SMS and recording history through the API for 90 days (8 of 15). A registered Swedish telecom operator, but no security.txt (404), disclosure policy, bug bounty or certification was found (3 of 20). 18+6+5+8+3 = 40.

Sinch Voice API + MCP 55

Voice v2 takes a project access key over Basic auth or as an OAuth 2.0 token. v1 uses an application key and secret with signed requests recommended. We found no per-key scopes (25 of 30). No read-only mode or confirmation step. The official MCP server's tool allow-list (--tags, or MCP_TAGS since 0.0.1-beta.7, 30 October) can leave out whole groups, and its released version runs over stdio only, as the Sinch messaging listing reads it (5 of 20). Calls carry untrusted caller speech. Callbacks are signed in v1 and v2, and we found no prompt-injection guidance (5 of 15). Call lookup and call lists by API, no audit log found (10 of 15). The trust centre lists ISO 27001:2022 and SOC 2 Type 2 reports, PCI and HIPAA, and Sinch's security contact for reports. No security.txt (404 on 2 November), no bug bounty and no advisories for @sinch/sdk-core, @sinch/mcp or sinch in OSV (10 of 20, as the Sinch messaging listing). 25 + 5 + 5 + 10 + 10 = 55.

46elks Voice API 20

No x402, MPP or L402 (0). Per-minute prices by destination are public without login, also in kronor, with incoming calls free (20). No free credit; only SMS to the test number +46700000000 costs nothing, and accounts are prepaid or invoiced against a deposit (0). A person signs up in a browser and copies the credentials (0). 0+20+0+0 = 20.

Sinch Voice API + MCP 35

No x402, MPP or L402 (0). The voice pricing page, re-read on 2 November, gives domestic outbound from $0.01 a minute with a downloadable Voice API price list, and only illustrative inbound, SIP, recording and number prices (15 of 20). Test credits and a test number on signup, with a payment method needed only to upgrade (20). A person signs up in a browser (0). 0 + 15 + 20 + 0 = 35.

46elks Voice API 47

Graded on the hosted REST and Realtime Voice APIs with the hosted lines. A status page exists, linked from 46elks.com/status on UptimeRobot (20). It draws its data by script from a path its robots.txt disallows, so no history was readable (5). SMS sending speed is documented in the FAQ, but no limit for calls, numbers or WebSocket sessions was found (5 of 15). llms.txt says to retry 5xx with exponential backoff and not to retry 4xx unchanged, with no Retry-After or idempotency for POST /calls (7 of 15). The SLA page commits to support hours and 24/7 error reporting with no uptime figure, and extended SLAs are by sales (0). Voice and Realtime Voice carry no beta label (10). 20+5+5+7+0+10 = 47.

Sinch Voice API + MCP 60

Statuspage at status.sinch.com with Voice components and history (20). Read from its own history and incident pages on 2 November (the 1 October count from IsDown, a third-party copy of the page, is struck). From 4 August to 2 November the calling incidents each name one region, one channel or a subset of calls. Calling in AP-Southeast-1 degraded from 04:50 to 07:23 UTC on 22 September (labelled critical, one region), PSTN outbound calls saw failed attempts from 05:51 to 09:05 UTC on 2 October (one channel, no region named, posted with no impact level), and Elastic SIP Trunking in US East had non-completed calls for 8 minutes on 9 September. On 26 October a planned change took the customer dashboard down and blocked traffic for a subset of accounts. Partial incidents read as minor, so minor only (20). No account rate limits published for voice. Batch calls take a maxCps setting (1 to 1,000 calls a second), which is a requested pace, not a published limit (0 of 15). The v2 OpenAPI file, readable on 2 November, documents a 429 answer with a Retry-After header on 15 of 17 operations, and an Idempotency-Key header (16 to 128 characters) whose repeats within 10 minutes return the cached response (15). No SLA found (0). Voice API v1 is generally available, but the v2 overview, llms.txt ("recommended for new builds/preview") and the pricing page (Voice Relay and Streams in Public Preview) label v2, the listed surface, as preview, and tell projects that must be GA to use v1. Mixed surfaces take part of the line, as gemini-api's 5 (5 of 10). 20 + 20 + 0 + 15 + 0 + 5 = 60.