{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/voice-cloning.professional-clone-training/",
    "json": "https://www.anchorterminal.com/niches/voice-cloning.professional-clone-training/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/voice-cloning.professional-clone-training/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/voice-cloning.professional-clone-training/index.min.md"
  },
  "markdown": "No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 0 | 3 | 22 | 7 | 2 |\n\n## What counts as done\n\nDocs state the minimum and recommended audio, the steps (upload, speaker separation, verification, training), the training time, and a status the agent can poll or a webhook; training failure returns a reason; the professional voice's price, slot limit and model binding are stated.\n\nHow agents ask for it: make a professional clone from my audiobook recordings; train a voice on 30 minutes of the actor; highest-quality clone for narration; fine-tune a voice on our studio recordings\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Cartesia Voice Cloning API + MCP (Cartesia AI, Inc.)**: Pro Voice Clone states 30 minutes minimum, training up to 3 hours, the Startup plan, and an API path (dataset, upload, fine-tune, list voices). No webhook or failure reason found, and slots per plan were not read on the pricing page.\n- **ElevenLabs Voice Cloning and Voice Design API (Eleven Labs Inc.)**: Docs give 30 minutes minimum and 1 to 3 hours recommended, noise removal, speaker separation, voice verification, and slots (none on Free or Starter, 1 on Creator and Pro, 3 on Scale, 10 on Business). No training-time estimate; the polling field and failure reasons are not in the guide.\n- **Gradium Voice Cloning and Voice Design (Gradium SAS)**: Pro Voice Clones need 30 minutes minimum (2 hours recommended) and are created only in Gradium Studio with a notification; no API, pollable state or failure reason.\n\n## Couldn't check\n\nThe docs were closed to us, or silent. These carry no mark either way.\n\n- **Fish Audio Voice Cloning API (Hanabi AI Inc.)**: The create schema has a pvc_release_state field, but the Professional Voice Clone page with its audio minimum and training time was not read.\n- **Inworld Instant Voice Cloning (Theai, Inc. dba Inworld AI)**: The guide links Professional Voice Cloning but the page was not read.\n- **Murf Voice Cloning API (Murf Inc.)**: Murf's terms bar automated access to murf.ai, so its API docs were not read this run, as in the 5 November check; no first-hand account names Murf.\n- **Resemble AI Voice Cloning API (Resemble AI, Inc.)**: Since 30 June 2026 API voices default to rapid clones (listing notes); no professional clone page was found in the docs read.\n- **Smallest.ai Instant Voice Clone (Smallest, Inc.)**: Only the instant clone API was read.\n\n- not this job: Hume Octave Voice Design and Cloning + MCP (Hume AI, Inc.): Hume's docs index now lists only Audio Decisions and Expression Measurement, and the voice overview and changelog redirect there; the TTS and EVI APIs, cloning and design included, are no longer documented after the 13 November 2026 end of access.\n- not this job: MiniMax Voice Clone and Voice Design (Nanonoble Pte. Ltd.): Only rapid cloning is documented; no professional training tier.\n- not this job: Soniox Voice Cloning (Soniox Inc.): Instant clones only; no professional training tier.\n- not this job: Speechify API Voice Cloning (Speechify, Inc.): The cloning overview documents zero-shot clones only; no professional training tier.\n- not this job: Ultravox Voice Cloning (Theai, Inc. dba Inworld AI): Instant clones only.\n- not this job: VoiceStudio (VoiceStudio maintainers): No fine-tuning or professional training flow in the MCP tools or README.\n\n## What stops agents finishing\n\n- one professional slot until the $299 Scale plan (ElevenLabs)\n- training failure fixed only by deleting and re-uploading (ElevenLabs help centre)\n- pre-Ultra voices cannot generate until upgraded (Resemble)\n- voices must be recomputed by hand after a new TTS model ships (Soniox)\n\n## Around it\n\nBefore: speech-to-text.long-recording-batch, voice-cloning.consented-clone-of-another. After: text-to-speech.long-form-narration.\n\n## Where this comes from\n\nWeight 7 of 100 in Voice cloning \u0026 custom voices: 2 of 34 accounts (a voice-actor professional clone for a launch, Cartesia's Pro-clone credit rate); the rest rests on ElevenLabs, Cartesia and Resemble docs. Kept as its own case because the steps, the verification and the price differ from instant clones\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/voice-cloning.professional-clone-training.json, or the MCP tool get_use_case with id voice-cloning.professional-clone-training. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Train a high-fidelity voice from long recordings",
        "url": ""
      }
    ],
    "description": "Train a high-fidelity voice from long recordings: 0 companies fully do it, 3 with a limit, 22 carry the tag. Every listing in Voice cloning \u0026 custom voices with the reason and a source.",
    "facts": null,
    "h1": "Train a high-fidelity voice from long recordings",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/voice-cloning.professional-clone-training/",
    "published": "",
    "section": "agents",
    "title": "Train a high-fidelity voice from long recordings | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/voice-cloning.professional-clone-training/"
  },
  "tokens": {
    "markdown": 1350,
    "slim": 330
  },
  "version": 1
}
