{
  "formatVersion": 1,
  "scope": "Curated public research extract; not the full raw run.",
  "canonical": "https://embiro.ai/research/orpheus-long-form-speech",
  "fieldNote": 14,
  "slug": "orpheus-long-form-speech",
  "title": "Faster speech, one language at a time.",
  "description": "Batching shortened one long English Orpheus run by 21%. Luganda and Swahili told a different story.",
  "category": "Speech",
  "art": "speech-wave",
  "thumbnail": {
    "src": "/research/thumbnails/orpheus-long-form-speech.webp",
    "alt": "A copper waveform flowing through three mint arches and speech tiles."
  },
  "date": "2026-10-12",
  "published": "2026-10-12",
  "updated": "2026-10-12",
  "author": "Embiro Labs Research",
  "status": "Exploratory benchmark",
  "headline": "A faster English path is not a universal upgrade.",
  "metric": "21.1%",
  "metricLabel": "less generation time · one English trial",
  "method": [
    "Same Cape Town T4, pinned Orpheus weights, FP16 and the same voice IDs. Compared the existing Transformers runtime with isolated vLLM 0.10.2 using PyTorch 2.8.",
    "Long text was split at sentence boundaries into chunks of at most 240 characters and joined in order. English used three chunks; Luganda and Swahili used two. vLLM batches of one, two and four were compared. No time stretching, silence trimming or weight quantization was introduced."
  ],
  "sections": [
    {
      "title": "A useful English result",
      "paragraphs": [
        "The 597-character English fixture took 154.75 seconds with sequential Transformers and 122.07 seconds with vLLM batch four: 21.1% less wall time in this single trial. Sequential vLLM was slower at 174.38 seconds. The improvement came from this batched serving configuration, not simply switching engines."
      ]
    },
    {
      "title": "Why the other languages kept their runtime",
      "paragraphs": [
        "Luganda took 73.82 seconds with Transformers versus 135.24 seconds with vLLM batch four. Audio length also changed from 19.71 to 31.83 seconds, so the outputs were not interchangeable. The long Swahili baseline failed on its first chunk at roughly 105 seconds; vLLM completed with a longer overall deadline. Completion under different deadlines is not evidence of a speedup."
      ]
    },
    {
      "title": "Decision after listening",
      "paragraphs": [
        "Following the comparison, the product owner listened to and accepted the longer English sample. The pilot adopted a conservative 600-character English path, while Luganda and Swahili retained their existing runtime and 300-character limit. This is acceptance of a sample, not a general unchanged-quality finding. Short English probes did not improve with vLLM.",
        "The best long-English configuration still allocated roughly USD 39.65 of busy host compute per million input characters. A subsidised API rate is separate from this measured cost."
      ]
    }
  ],
  "limitations": [
    "Small diagnostic samples, not a production SLA or a population accuracy estimate. Different output lengths affect completion time.",
    "One long fixture per language/configuration; not a repeated speed estimate. Samples vary in audio duration. No blind listening panel, MOS score or broad language-quality conclusion.",
    "The Swahili failure remains part of the record and must not be removed from a completion comparison.",
    "Busy-compute estimates allocate the whole host rate to the measured operation. They exclude idle time, startup, storage, network and taxes; they are not customer API prices or marginal savings. Rates are the recorded October 2026 inputs, not a current quote."
  ],
  "tables": [
    {
      "title": "Long-text configurations",
      "columns": [
        "Language",
        "Runtime / batch",
        "Characters",
        "Generation (s)",
        "Audio (s)"
      ],
      "rows": [
        [
          "EN",
          "transformers-b1",
          "597",
          "154.75",
          "40.28"
        ],
        [
          "EN",
          "vllm-b1",
          "597",
          "174.38",
          "40.79"
        ],
        [
          "EN",
          "vllm-b2",
          "597",
          "152.28",
          "40.45"
        ],
        [
          "EN",
          "vllm-b4",
          "597",
          "122.07",
          "40.87"
        ],
        [
          "LG",
          "transformers-b1",
          "349",
          "73.82",
          "19.71"
        ],
        [
          "LG",
          "vllm-b1",
          "349",
          "143.56",
          "31.40"
        ],
        [
          "LG",
          "vllm-b2",
          "349",
          "135.02",
          "31.83"
        ],
        [
          "LG",
          "vllm-b4",
          "349",
          "135.24",
          "31.83"
        ],
        [
          "SW",
          "vllm-b1",
          "391",
          "211.35",
          "44.12"
        ],
        [
          "SW",
          "vllm-b2",
          "391",
          "173.44",
          "44.20"
        ],
        [
          "SW",
          "vllm-b4",
          "391",
          "174.23",
          "44.20"
        ]
      ],
      "note": "Lower generation time is preferable only when content and voice are acceptable. Missing Transformers Swahili row: failed/truncated, not a zero-second result."
    }
  ],
  "references": [],
  "audio": [],
  "evidence": [
    {
      "file": "README.md",
      "sha256": "78a3aeccd82b029fff82184eb7dbfc65d4c8d5267474920bbf2d1812d61c41c5"
    },
    {
      "file": "comparison-summary.json",
      "sha256": "af6c89c02e774eac799e778f4ab3f749d507715a1ef7cd39760ae4d20d6be153"
    }
  ]
}