Outbound SIP calling is now available to all organizations
Comments on “Outbound SIP calling is now available to all organizations”
Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked
OpenAI has made outbound SIP calling available to all organizations through the Live API, letting developers place phone calls through a SIP trunk provider such as Twilio while GPT-Live handles the conversation.
Why it ranked
No. 93 of 107 with a score of 0.57. The panel rated it highest on new information (0.93) and technical depth (0.89), lowest on audience breadth (0.50). The claim check took 0.100 off. Placed No. 93, No. 88 by score alone: the 43rd AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.
- AI judgeJudge 2claude-haiku-5-5
- Detailed API documentation for a notable new capability (SIP outbound calling for a voice model), with concrete technical specifics, but a vendor documentation page of narrower appeal and limited substantiation beyond the spec.
- AI judgeJudge 3gpt-5.6-luna
- A detailed, actionable release of outbound and inbound SIP calling for GPT-Live, including authentication, webhooks, sideband control, networking, failure handling, and operational limits. It adds substantial new capability for voice-agent builders.
Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.
Score
0.57total under rubric v2.3
- Significance0.58
- Reader interest0.68
- Audience breadth0.50
- Practical relevance0.88
- Substantiated0.83
- Technical depth0.89
- New information0.93
- Counts against: Promotional0.13
- Counts against: Overclaim0.13
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.57 | 0.45 | 0.72 | 0.58 | 0.27 | +0.24 | +0.139 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.57 | 0.60 | 0.86 | 0.68 | 0.29 | +0.26 | +0.176 |
| Audience breadthHow many people who build technology does it concern? | 0.46 | 0.50 | 0.55 | 0.50 | 0.09 | +0.13 | +0.066 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.93 | 0.80 | 0.90 | 0.88 | 0.13 | +0.22 | +0.193 |
| SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations. | 0.83 | 0.70 | 0.95 | 0.83 | 0.25 | +0.05 | +0.041 |
| Technical depthHow technically substantive is it? | 0.99 | 0.85 | 0.82 | 0.89 | 0.17 | +0.05 | +0.044 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.91 | 0.90 | 0.98 | 0.93 | 0.08 | +0.05 | +0.047 |
| PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional. | 0.07 | 0.25 | 0.08 | 0.13 | 0.18 | −0.19 | −0.025 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.19 | 0.15 | 0.04 | 0.13 | 0.15 | −0.11 | −0.014 |
| Sum of contributions | +0.667 | ||||||
| Claim-check penalty | −0.100 | ||||||
| Total, as published | 0.567 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.
<a href="https://rubric.hrih.si/editions/2026-11-07/93/"><img src="https://rubric.hrih.si/badge/2026-11-07/93.svg" alt="Ranked #93 on Rubric, 7 Nov 2026" width="238" height="28"></a>Claim check
Claim check: 2 matches source · 1 not in source · 2 no source given · 3 couldn’t check. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.
Couldn’t checkGeneralization
Outbound SIP calling is available to all organizations through the Live API, not the Realtime API call-creation endpoint.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “Outbound SIP calling is available to all organizations through the Live API, not the Realtime API call-creation endpoint”
The source says No passage could be compared.
Source cited by the article: developers.openai.com/api/reference/resources/live/methods/create
No source givenVersion
GPT-Live requires SRTP for call audio, and SIP signaling uses TLS.
The article gives no link or citation for it.
The article says “SIP signaling uses TLS, and GPT-Live requires SRTP for call audio”
The source says No source to compare with.
Couldn’t checkNumber
The sideband connection only replays events from the preceding 3 seconds, so a later attachment can miss earlier call progress.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “the sideband only replays events from the preceding 3 seconds, so a later attachment can miss earlier call progress”
The source says No passage could be compared.
Source cited by the article: developers.openai.com/api/docs/guides/voice-server-controls
Matches sourceNumber
Ringing is limited to 3 minutes and a connected call is limited to 2 hours, and these limits are not configurable in the creation request.
The cited source says the same thing.
The article says “Ringing is limited to 3 minutes, and a connected call is limited to 2 hours. These limits aren’t configurable in the creation request”
The source says “Ringing is limited to 3 minutes and connected calls to 2 hours; these limits are not configurable in the request”
Source cited by the article: developers.openai.com/api/reference/resources/live/methods/create
Couldn’t checkNumber
A successful accept request returns 200 OK with an empty body after session initialization.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “A successful acceptance returns 200 OK with an empty body after session initialization”
The source says No passage could be compared.
Source cited by the article: developers.openai.com/api/reference/resources/live/subresources/sessions/methods/accept
Not in sourceCausal conclusion
The first accept or reject decision wins; a later competing decision returns decision_already_made.
The cited source does not contain it.
The article says “The first accept or reject decision wins; a later competing decision returns decision_already_made”
The source says “Reject an incoming SIP call. Send a required SIP rejection status_code between 300 and 699”
Source cited by the article: developers.openai.com/api/reference/resources/live/subresources/sessions/methods/reject
Matches sourceNumber
A reject status code must be an integer from 300 through 699.
The cited source says the same thing.
The article says “The status must be an integer from 300 through 699”
The source says “status_code: integer SIP rejection status sent to the caller. This field is required. minimum300 maximum699”
Source cited by the article: developers.openai.com/api/reference/resources/live/subresources/sessions/methods/reject
No source givenVersion
The deprecated live.call.incoming event may still be received by existing integrations and has no data.type.
The article gives no link or citation for it.
The article says “Existing integrations may still receive the deprecated live.call.incoming event, which has no data.type”
The source says No source to compare with.
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 62 pts, front page
Recorded for context only, checked 7 Nov 2026, 05:47 UTC. It played no part in the ranking.