🐦 Twitter Post Details

Viewing enriched Twitter post

@thejessezhang

One of the trickiest problems you run into with voice AI in the real world is that people often call in messy environments. There might be other voices in the background, or the person might be talking to other people at the same time. Super cool work from Decagon Labs on how we've tackled this problem!

📊 Media Metadata

{
  "score": 0.36,
  "score_components": {
    "author": 0.09,
    "engagement": 0.0,
    "quality": 0.06000000000000001,
    "source": 0.135,
    "nlp": 0.05,
    "recency": 0.025
  },
  "scored_at": "2026-08-28T10:01:25.151030",
  "import_source": "api_import",
  "source_tagged_at": "2026-08-28T10:01:25.151044",
  "enriched": true,
  "enriched_at": "2026-08-28T10:01:25.151046"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2093129820431638922",
  "url": "https://x.com/thejessezhang/status/2093129820431638922",
  "twitterUrl": "https://twitter.com/thejessezhang/status/2093129820431638922",
  "text": "One of the trickiest problems you run into with voice AI in the real world is that people often call in messy environments.\n\nThere might be other voices in the background, or the person might be talking to other people at the same time.\n\nSuper cool work from Decagon Labs on how we've tackled this problem!",
  "source": "Twitter for iPhone",
  "retweetCount": 3,
  "replyCount": 0,
  "likeCount": 27,
  "quoteCount": 0,
  "viewCount": 5712,
  "createdAt": "Fri Aug 28 00:13:32 +0000 2026",
  "lang": "en",
  "bookmarkCount": 12,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2093129820431638922",
  "displayTextRange": [
    0,
    278
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "thejessezhang",
    "url": "https://x.com/thejessezhang",
    "twitterUrl": "https://twitter.com/thejessezhang",
    "id": "1454218999504408581",
    "name": "Jesse Zhang",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1987633437843566592/PeXsIDsc_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1454218999504408581/1769625794",
    "description": "",
    "location": "SF Bay Area",
    "followers": 98923,
    "following": 198,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Oct 29 22:50:14 +0000 2021",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 594,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 46,
    "statusesCount": 286,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {
      "label": {
        "badge": {
          "url": "https://pbs.twimg.com/profile_images/2000983714843779083/k8lZoNew_bigger.jpg"
        },
        "description": "Decagon",
        "url": {
          "url": "https://twitter.com/DecagonAI",
          "url_type": "DeepLink"
        },
        "user_label_display_type": "Badge",
        "user_label_type": "BusinessLabel"
      }
    },
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2074154325933424861"
    ],
    "profile_bio": {
      "description": "CEO @DecagonAI",
      "entities": {
        "description": {
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                4,
                14
              ],
              "name": "",
              "screen_name": "DecagonAI"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "jessezhang.org",
              "expanded_url": "https://jessezhang.org",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/pvxP9IIePI"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2093105819063906344",
    "url": "https://x.com/DecagonAI/status/2093105819063906344",
    "twitterUrl": "https://twitter.com/DecagonAI/status/2093105819063906344",
    "text": "Conversational voice agents need to know when a different person is speaking, but not every background voice should count.\n\nWe combined speaker embeddings with a post-trained audio-language model to determine when a speaker change matters. https://t.co/Cg5HKtyaUf",
    "source": "Twitter for iPhone",
    "retweetCount": 4,
    "replyCount": 7,
    "likeCount": 31,
    "quoteCount": 3,
    "viewCount": 7552,
    "createdAt": "Thu Aug 27 22:38:09 +0000 2026",
    "lang": "en",
    "bookmarkCount": 17,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2093105819063906344",
    "displayTextRange": [
      0,
      263
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "DecagonAI",
      "url": "https://x.com/DecagonAI",
      "twitterUrl": "https://twitter.com/DecagonAI",
      "id": "1741997980021071872",
      "name": "Decagon",
      "isVerified": false,
      "isBlueVerified": false,
      "verifiedType": "Business",
      "profilePicture": "https://pbs.twimg.com/profile_images/2000983714843779083/k8lZoNew_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/1741997980021071872/1787853652",
      "description": "",
      "location": "San Francisco",
      "followers": 5859,
      "following": 21,
      "status": "",
      "canDm": false,
      "canMediaTag": true,
      "createdAt": "Tue Jan 02 01:41:12 +0000 2024",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 739,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 172,
      "statusesCount": 633,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [],
      "profile_bio": {
        "description": "AI agents for concierge customer experiences. Trusted by the world's most impactful companies.",
        "entities": {
          "description": {},
          "url": {
            "urls": [
              {
                "display_url": "decagon.ai",
                "expanded_url": "https://decagon.ai",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/61sa7CPka9"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {},
    "card": null,
    "place": {},
    "entities": {
      "urls": [
        {
          "display_url": "x.com/i/article/2093…",
          "expanded_url": "https://x.com/i/article/2093044778615390208",
          "indices": [
            240,
            263
          ],
          "url": "https://t.co/Cg5HKtyaUf"
        }
      ]
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "communityInfo": null,
    "article": {
      "title": "Detecting Relevant Speaker Changes with Audio-Native Models",
      "preview_text": "By @alon_rag and @EveraertDante\n \nThe problem: knowing when another user joins the conversation\nIn customer support, voice agents need to know not only what was said, but who is participating. If",
      "cover_media_img_url": "https://pbs.twimg.com/media/HQw0k9OaQAA888o.jpg"
    }
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}