Head to head · Voice agents · October 2026 research run

Amazon Nova 2 Sonic vs fone.me

Amazon Nova 2 Sonic scores 67.6 (B) on agent readiness against fone.me's 28.3 (F), and leads in 6 of 7 scored categories. fone.me leads on payments & pricing. Both do voice agents.

Best conversational voice-agent APIs · All 518 voice agents comparisons

Which one, for what

Amazon Nova 2 Sonic B

Best for Voice agents on AWS, call centres on Amazon Connect, teams that want IAM and in-account data handling.

Ahead on

  • Reliability, 95 against 15
  • Schema & documentation, 75 against 31
  • Agent ergonomics, 64 against 29
  • Security & auth, 77 against 30
  • Maintenance & community, 50 against 23
  • Transparency & trust, 79 against 23

Watch for

Connections end after 8 minutes, so long calls need the session-continuation pattern

fone.me F

Best for Agents acting for a person who need to reach a freelancer's, shop's or small business's own AI agent at its fone.me link to ask a question, request a booking or quote or leave a message, and owners who want an answering agent on a link, WhatsApp, Telegram and a $9.99 number without building one.

Ahead on

  • Payments & pricing, 50 against 10

Also in its favour

  • No key needed to call it
  • A hosted endpoint, with nothing to install

Watch for

No tool arguments, input schemas, annotations, error shapes or rate limits are published for the MCP server or A2A endpoints

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reliability Amazon Nova 2 Sonic +80

Amazon Nova 2 Sonic 95

Hosted reading. AWS Health Dashboard with per-service, per-Region history (20). The dashboard history file (newest event 30 October 2026) lists no Bedrock event in the 90 days from 8 August, and the 3 September us-west-2 event names STS, Connect and IAM Identity Center, not Bedrock. The public dashboard records broad events only, so 25 of 30, as amazon-nova-embeddings was read. Quotas published, 20 concurrent requests per Region, not adjustable (15). The stream API lists ThrottlingException (429), ServiceUnavailableException (503), ModelTimeoutException (408) and ModelStreamErrorException (424), Bedrock's troubleshooting guide advises backoff with jitter, and the 8-minute connection limit comes with a session-continuation sample (15). Bedrock's SLA of 99.9 per cent a month per Region for model APIs, as read for amazon-nova-embeddings on 1 November (10). Generally available since 2 December 2025 (10). 20 + 25 + 15 + 15 + 10 + 10 = 95.

fone.me 15

Hosted reading, for the MCP server and A2A endpoints and the service behind them. No status page is linked from llms.txt, the home page or any guide page read, and https://www.fone.me/status failed to load (0). No readable incident history, so the floor (5). No request rate limit for the MCP server, the search API or A2A is published; the only limits are on the agent's own outbound calls (8 am to 9 pm in the callee's time zone, 'limited per day' with no number), which are not request limits (0 of 15). No 429, overload or retry guidance and no idempotency key for message_agent or message/send (0 of 15). No SLA (0). Nothing on the MCP server, the agent cards or llms.txt is marked beta or preview, and the MCP repository's server.json is version 1.0.0 (10). 0+5+0+0+0+10 = 15.

Transparency & trust Amazon Nova 2 Sonic +56

Amazon Nova 2 Sonic 79

Closed model under the AWS Service Terms, with Apache-2.0 SDKs and samples (15). Bedrock stores no inputs or outputs by default and model providers can't see them, Sonic isn't on the abuse-detection page's list of models whose traffic is stored, and section 50.3 doesn't list Bedrock among services whose content improves AWS services, as read for amazon-nova-embeddings on 1 November (22 of 30). Bedrock's lifecycle policy for models launched before 7 September 2026 promises 12 months and a Legacy period of at least 6 months, but the March and May refreshes changed the model in place under the same ID (15 of 20). Regions are listed, with sub-processors not read (12 of 20). Total 64.

fone.me 23

Closed service. Terms of service exist at /terms but draw by script, so their content, governing law and the company they name are unchecked; no company, address or country of incorporation appears on any page read, llms.txt says San Francisco, and the MCP repository has no licence (5 of 30). Data handling was read only from guide pages, which say only the owner sees their calls and messages, calls are transcribed and callers told so, and private categories are withheld. The privacy policy and data-deletion page draw by script, so no retention period, recording statement, DPA or AI-training statement was read (8 of 30). No deprecation policy or dated notices (0). No subprocessors, telephony, model or hosting providers or data locations are named on any page read; the demo agent card's icon is served from Cloudinary (0 of 20). 5+8+0+0 = 13.

Security & auth Amazon Nova 2 Sonic +47

Amazon Nova 2 Sonic 77

SigV4 with IAM roles and temporary credentials scoped per model ARN, as the Sonic quickstart signs (30). Tools run in the client, so side effects are the developer's to approve, and IAM can restrict which models a role invokes, with no approval step in the API (12 of 20). The model listens to callers and acts on tool results, and no prompt-injection guidance was found in the Sonic guide (5 of 15). CloudTrail logs Bedrock API calls, read as amazon-nova-embeddings was (12 of 15). VDP on HackerOne, Bedrock in SOC scope and a valid security.txt on aws.amazon.com, with no paid bounty, as on the other AWS listings (18 of 20). Total 77.

fone.me 30

No credential exists for callers. llms.txt gives auth 'none', the README says the server is 'public, like the links themselves', and the two agent cards read declare no security scheme. There is nothing to leak or rotate, but fone.me and an owner can tell callers apart only by the name they give ('Maria via ChatGPT' in the README) and by traffic, and no caller identity or verification is documented (10 of 30). Three of four MCP tools are lookups; message_agent and A2A message/send reach any owner's agent. On the owner's side the vendor says the agent asks before agreeing to anything or spending money, the owner approves what it will say before a call, outbound calls run only 8 am to 9 pm local, pause when reported and stop permanently on request, and the owner can take over any chat. No read-only mode and no confirmation on the caller's side (8 of 20). message_agent returns text generated from what the owner taught the agent, and every agent on the platform reads messages from anyone; the only guidance is the how-it-works statement that the agent keeps relationship status, health, money and address private, with no documented prompt-injection or spam handling for the open channel, and the call-screening page says it does not promise to block calls (4 of 15). Owners see every call and chat with a transcript in one inbox; nothing is logged for the calling agent (8 of 15). /.well-known/security.txt answers with the app shell, and no disclosure policy, bug bounty or certification appears on any page read (0 of 20). 10+8+4+8+0 = 30.

Schema & documentation Amazon Nova 2 Sonic +44

Amazon Nova 2 Sonic 75

The Bedrock service model types InvokeModelWithBidirectionalStream, but the Sonic events inside it (session, prompt, content, tool and usage events) are JSON payloads documented only in the guide, with no schema file (12 of 25). llms.txt and Markdown copies of the Nova 2 guide (10). Guides on the event lifecycle, barge-in, turn-taking, async tools and chat history say when and how to use each (16 of 20). Event fields are documented as JSON examples and tables, not typed schemas (10 of 15). Sample repositories in several languages and the API's exceptions with HTTP codes (12 of 15). Release notes and document history, with in-place model refreshes and a versioned model ID (15). Total 75.

fone.me 31

MCP reading, since the MCP server is what an outside agent calls. No tool arguments or input schemas are published in llms.txt, the guide pages or the GitHub README, and robots.txt disallows /mcp, so no session was opened and tools/list was not read. Per-link A2A agent cards are machine-readable JSON (protocol 0.3.0, JSONRPC, input and output modes, skills with examples) and server.json names the remote, but neither types the MCP tools (8 of 25). llms.txt is a real document for agents covering the MCP server, A2A, the search API and the widget (10). Each tool has a one-line purpose in llms.txt and the README, and the how-it-works page states what the agent will and won't do; nothing says when not to use a tool (6 of 20). No typed inputs, enums, constraints or required fields published (0 of 15). Example prompts in the README, per-skill examples in agent cards and widget code for eight site builders; no error response is documented (4 of 15). server.json and the agent cards carry version 1.0.0 and the cards a protocol version; no changelog (3 of 15). 8+10+6+0+4+3 = 31.

Payments & pricing fone.me +40

Amazon Nova 2 Sonic 10

No x402, MPP or L402 (0). The Nova and Bedrock pricing pages carry a speech-to-speech table drawn by script, so the per-token prices weren't read and this line scores absent, which is our reader's limit and not the vendor's (0). New accounts get up to $200 in Free Tier credits, and the Free Tier FAQ says most new customers need no payment method, read as half on the other AWS listings (10). A person signs up for an AWS account in a browser (0). Total 10.

fone.me 50

No x402, MPP or L402 on any page read (0). Premium is $9.99 a month on llms.txt and the Smith.ai comparison page, with no minute allowance or per-call price (10 of 20). The MCP server, search API and A2A endpoints are free with no account, and the agent, first link and chat button are free for owners; no page mentions a card for any of these (20). An outside agent needs no sign-up, key or payment to find and message an agent (20). 0+10+20+20 = 50.

Agent ergonomics Amazon Nova 2 Sonic +35

Amazon Nova 2 Sonic 64

Scored as an API. Responses carry transcripts of both sides and usage events, chat history is capped at 200 KB and can be injected once per session (15 of 25). Output controls are voice, turn-taking sensitivity and text or audio input (12 of 20). Typed exceptions with HTTP codes, while errors inside the event stream are less documented (15 of 20). Asynchronous tool calls let the model keep talking, and AWS samples show how to resume after the 8-minute limit, with nothing on repeating tool side effects after a reconnect (12 of 20). A session needs a sequence of start events before audio. The JavaScript SDK is current, but the Python SDK the quickstart uses is pre-alpha and needs Python 3.12 (10 of 15). Total 64.

fone.me 29

MCP reading. Four tools named in llms.txt, a small set, but their definitions were not read, so short of full marks (18 of 25). find_agents searches by what someone does and the search API takes a query; no limit, paging or output-size controls are documented (3 of 20). No error codes or messages documented for the MCP server, the search API or A2A (0 of 20). No readOnlyHint or destructiveHint seen and no idempotency key; the three lookups are read-only by name and description, while message_agent writes to a real person's inbox and continues the conversation across calls (2 of 20). No credentials, no configuration beyond the URL, and few stated inputs; no SDK in any language (6 of 15). 18+3+0+2+6 = 29.

Score by category

CategoryWeight this runAmazon Nova 2 Sonicfone.meEdge
Reliability16%209515Amazon Nova 2 Sonic +80
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27531Amazon Nova 2 Sonic +44
Agent ergonomics13%16.26429Amazon Nova 2 Sonic +35
Security & auth14%17.57730Amazon Nova 2 Sonic +47
Payments & pricing10%12.51050fone.me +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.85023Amazon Nova 2 Sonic +27
Transparency & trust7%8.87923Amazon Nova 2 Sonic +56
Negative events≤1500
TotalB 67.6/100F 28.3/100

Facts side by side

FactAmazon Nova 2 Sonicfone.me
KindHTTP APIPlatform
VendorAmazon Web ServicesFone
Hosted endpointno (local only)https://www.fone.me/mcp
TransportsHTTPStreamable HTTP
AuthAPI keyNone
PricingPay per useFreemium
x402nono
LicencenoneProprietary hosted service. Terms of service at https://www.fone.me/terms, whose text draws by script and could not be read on 5 November 2026; no company is named on any page read. No source, SDK or package is published
Tools exposed04
Read-only variant documentednono
llms.txtyesyes
Last release2026-05-282026-10-05
Terms last updated2026-10-01couldn't be read
Privacy policy last updated2026-05-18couldn't be read
Customer content may train modelsyes, with an opt-outcouldn't be read
Terms restrict automated accessyescouldn't be read
Terms restrict benchmarkingyescouldn't be read
Terms or service can change without noticeyescouldn't be read
Arbitration or class-action waivernot found in the textcouldn't be read

Verdicts

Amazon Nova 2 Sonic

Nova 2 Sonic runs speech-to-speech conversations with asynchronous tools on Bedrock, with IAM scoping, no default storage of inputs and a 99.9 per cent SLA. Sessions cut off at 8 minutes, the Python SDK is pre-alpha, and the event payloads have no schema file. Prices are in a script-drawn table we couldn't read.

fone.me

Any agent can find a fone.me link and message its owner's agent through a keyless MCP server or A2A, with no sign-up or cost, and owners see every conversation in one inbox. Tool schemas, rate limits and abuse controls for that open channel are unpublished, the terms and privacy policy draw by script, and no company is named.

Before you call either

Amazon Nova 2 Sonic

  1. Plan a reconnect before 8 minutes and replay chat history (up to 200 KB) at the start of the new session
  2. Send session, prompt and content start events in order before any audio
  3. Make tool calls safe to repeat, since a reconnect can replay them
  4. Back off on ThrottlingException and stay within 20 concurrent sessions per Region
  5. Use the polyglot voices TIFFANY or MATTHEW when callers may switch language

fone.me

  1. Connect to https://www.fone.me/mcp with no credentials; use find_agents or get_agent before message_agent so the message goes to the right person's link.
  2. Say who you are acting for in every message_agent call; the owner reads it in an inbox as a named conversation, and conversations continue across calls.
  3. Treat replies as the owner's agent speaking from what it was taught, not a commitment; the vendor says it asks its owner before agreeing to anything or spending money.
  4. Read a link's agent card at /{link}/.well-known/agent-card.json for its skills before using A2A message/send at /{link}/a2a.
  5. Don't send personal or payment details through message_agent; no retention or privacy terms for agent-to-agent messages could be read.

Questions

Which is better for AI agents, Amazon Nova 2 Sonic or fone.me?

Amazon Nova 2 Sonic scores 67.6 (B) on agent readiness against fone.me's 28.3 (F), and leads in 6 of 7 scored categories. fone.me leads on payments & pricing.

Can an agent call Amazon Nova 2 Sonic and fone.me without installing anything?

No hosted endpoint is listed for Amazon Nova 2 Sonic. fone.me has a hosted endpoint at https://www.fone.me/mcp.

Other comparisons with Amazon Nova 2 Sonic or fone.me

Machine-readable

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.