Fish Audio: Voice Clone to Speech

Clone any voice from a short recording, then use it to speak any script with Fish Audio. Record 2-3 clips of 15-20 seconds, connect them to the Instant Voice Clone node, and the cloned voice feeds straight into text to speech with no training wait. Add emotion tags to control how your cloned voice delivers each line. Great for personalized narration, character voices, and content in your own voice.

Download Workflow Try in Cloud

About

This ComfyUI workflow lets you clone any voice from a few short recordings and immediately synthesize new speech with that voice using Fish Audio. In Option 1 (Voice Clone), you feed clean voice samples from RecordAudio or LoadAudio into FishAudioInstantVoiceClone. The node returns a clone handle that plugs straight into FishAudioTextToSpeech, so you can type any script and get an instant read—no training wait. In Option 2 (Preset Audio), you skip cloning entirely by selecting a built-in voice with FishAudioVoiceSelector and send it directly to FishAudioTextToSpeech for quick, predictable results.

Under the hood, the audio path is simple and fast: RecordAudio/LoadAudio → FishAudioInstantVoiceClone (Option 1) or FishAudioVoiceSelector (Option 2) → FishAudioTextToSpeech → SaveAudioAdvanced. Text prompts can include emotion/style tags supported by Fish Audio to influence delivery (tone, pacing, emphasis). SaveAudioAdvanced lets you export the result in your preferred format and quality. All Fish Audio nodes are API-based, so you’ll authenticate with your ComfyUI account and pay per use.

For best clones, provide 2–3 samples of 15–20 seconds each with clear, expressive speech and minimal background noise. Vary your prosody slightly (neutral, upbeat, calm) so the Instant Voice Clone has enough information to capture timbre and delivery. Then iterate quickly: adjust your script and tags, re-queue, and export takes until you land the read you want.

What you provide

Reading the workflow

Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.

Try in Cloud

Output

Use this workflow from code

Generated from the workflow graph and inputs when possible; stored examples are shown otherwise. Review credentials and endpoints before running code, which may incur charges.

Get API key

What you need

Runs on: Comfy Cloud
Key: COMFY_API_KEY
Your files: Uploaded by the code from their urls

Needs a paid Cloud plan and credits.

Download API JSON

# Python 3.10+: pip install comfy-sdk==0.4.0
import os

from comfy_sdk import Comfy

api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
    "1": {
        "class_type": "FishAudioTextToSpeech",
        "inputs": {
            "model": "s2.1-pro",
            "model.normalize": True,
            "model.speed": 1,
            "model.temperature": 0.7,
            "model.top_p": 0.7,
            "model.voices.voice0": [
                "10",
                0
            ],
            "model.volume": 0,
            "seed": 731226986,
            "text": "[curious] Want a voice that sounds exactly like you?\n[calm] Record a short clip, clone it with Fish Audio, and type your script.\n[confident] Your voice, saying anything. Right in ComfyUI."
        },
        "_meta": {
            "title": "Fish Audio Text to Speech"
        }
    },
    "5": {
        "class_type": "SaveAudioAdvanced",
        "inputs": {
            "audio": [
                "1",
                0
            ],
            "filename_prefix": "audio/Fish_audio_t2s",
            "format": "mp3",
            "format.quality": "V0"
        },
        "_meta": {
            "title": "Save Audio (Advanced)"
        }
    },
    "10": {
        "class_type": "FishAudioInstantVoiceClone",
        "inputs": {
            "enhance_audio_quality": True,
            "files.audio0": [
                "11",
                0
            ]
        },
        "_meta": {
            "title": "Fish Audio Instant Voice Clone"
        }
    },
    "11": {
        "class_type": "LoadAudio",
        "inputs": {
            "audio": "UPLOADED_audio_FILENAME"
        },
        "_meta": {
            "title": "Load Audio"
        }
    }
})
# Replace each example.com URL with a public URL of your file.
workflow.set_input("11", "audio", client.assets.from_url("https://example.com/replace-with-a-url/audio"))

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)

API documentation

Fish Audio: Voice Clone to Speech

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

How many and what kind of samples do I need for a good clone?

Do I need a GPU or model training to clone a voice?

How do I control emotion, speed, or pauses in the speech?

What’s the difference between Voice Clone and Preset Audio paths?