オープンソースTTSモデル完全比較2026：Qwen3-TTS・Chatterbox・Fish Speech・CosyVoice・IndexTTS2を実際に動かして検証した

#!/usr/bin/env python3
from __future__ import annotations

import argparse
import importlib.util
from pathlib import Path

import soundfile as sf
import torch
from qwen_tts import Qwen3TTSModel


DEFAULT_REF_AUDIO = (
    "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone.wav"
)
DEFAULT_REF_TEXT = (
    "Okay. Yeah. I resent you. I love you. I respect you. But you know what? "
    "You blew it! And thanks to you."
)


def resolve_device(device: str) -> str:
    if device == "cuda":
        return "cuda:0" if torch.cuda.is_available() else "cpu"
    if device.startswith("cuda") and not torch.cuda.is_available():
        return "cpu"
    return device


def resolve_dtype(device: str) -> torch.dtype:
    if not device.startswith("cuda"):
        return torch.float32
    bf16_supported = bool(
        hasattr(torch.cuda, "is_bf16_supported") and torch.cuda.is_bf16_supported()
    )
    return torch.bfloat16 if bf16_supported else torch.float16


def resolve_attention(device: str, requested: str) -> str:
    if requested != "auto":
        return requested
    if device.startswith("cuda") and importlib.util.find_spec("flash_attn") is not None:
        return "flash_attention_2"
    return "sdpa" if device.startswith("cuda") else "eager"


def main() -> int:
    p = argparse.ArgumentParser()
    p.add_argument(
        "--text",
        default="これはQwen3のvoice clone動作確認です。参照音声に近い声で読み上げます。",
    )
    p.add_argument("--out", default="outputs/qwen3_voice_clone.wav")
    p.add_argument("--device", default="cuda")
    p.add_argument("--language", default="Japanese")
    p.add_argument("--model", default="Qwen/Qwen3-TTS-12Hz-0.6B-Base")
    p.add_argument("--ref-audio", default=DEFAULT_REF_AUDIO)
    p.add_argument("--ref-text", default=DEFAULT_REF_TEXT)
    p.add_argument("--x-vector-only-mode", action="store_true")
    p.add_argument(
        "--attn-implementation",
        default="auto",
        choices=["auto", "flash_attention_2", "sdpa", "eager"],
    )
    args = p.parse_args()

    device = resolve_device(args.device)
    dtype = resolve_dtype(device)
    attn_implementation = resolve_attention(device, args.attn_implementation)

    if args.x_vector_only_mode:
        ref_text = None
    else:
        ref_text = args.ref_text.strip()
        if not ref_text:
            raise SystemExit("--ref-text is required unless --x-vector-only-mode is set")

    model = Qwen3TTSModel.from_pretrained(
        args.model,
        device_map=device,
        dtype=dtype,
        attn_implementation=attn_implementation,
    )
    wavs, sr = model.generate_voice_clone(
        text=args.text,
        language=args.language,
        ref_audio=args.ref_audio,
        ref_text=ref_text,
        x_vector_only_mode=args.x_vector_only_mode,
    )

    out = Path(args.out)
    out.parent.mkdir(parents=True, exist_ok=True)
    sf.write(out, wavs[0], sr)
    print(out)
    return 0


if __name__ == "__main__":
    raise SystemExit(main())

#!/usr/bin/env python3
from __future__ import annotations

import argparse
from pathlib import Path

import torch
import torchaudio as ta
from chatterbox.mtl_tts import ChatterboxMultilingualTTS
from chatterbox.tts import ChatterboxTTS


def main() -> int:
    p = argparse.ArgumentParser()
    p.add_argument("--text", default="Hello, this is a Chatterbox test.")
    p.add_argument("--out", default="outputs/chatterbox.wav")
    p.add_argument("--device", default="cuda")
    p.add_argument(
        "--variant", choices=["turbo", "multilingual"], default="multilingual"
    )
    p.add_argument("--language-id", default="ja")
    p.add_argument("--audio-prompt-path", default=None)
    args = p.parse_args()

    device = (
        "cuda:0"
        if args.device.startswith("cuda") and torch.cuda.is_available()
        else "cpu"
    )

    if args.variant == "multilingual":
        model = ChatterboxMultilingualTTS.from_pretrained(device=device)
        wav = model.generate(
            args.text,
            language_id=args.language_id,
            audio_prompt_path=args.audio_prompt_path,
        )
    else:
        model = ChatterboxTTS.from_pretrained(device=device)
        wav = model.generate(args.text, audio_prompt_path=args.audio_prompt_path)

    out = Path(args.out)
    out.parent.mkdir(parents=True, exist_ok=True)
    ta.save(str(out), wav, model.sr)
    print(out)
    return 0


if __name__ == "__main__":
    raise SystemExit(main())

sudo apt-get install -y portaudio19-dev libsox-dev ffmpeg build-essential
uv sync --python 3.12 --extra cu129
hf download fishaudio/s2-pro --local-dir checkpoints/s2-pro

# Step 1: semantic tokens を生成
uv run python fish_speech/models/text2semantic/inference.py \
  --text 'こんにちは。Fish Speech のコマンドライン推論を確認しています。' \
  --output-dir output/demo \
  --device cuda

# Step 2: tokens を wav に変換
uv run python fish_speech/models/dac/inference.py \
  -i output/demo/codes_0.npy \
  -o output/demo/generated.wav \
  --checkpoint-path checkpoints/s2-pro/codec.pth \
  -d cuda

# 1. Whisperで参照音声を書き起こし
python - <<'PY'
from transformers import pipeline
pipe = pipeline(
    "automatic-speech-recognition",
    model="openai/whisper-large-v3-turbo",
    device="cuda:0",
)
res = pipe("path/to/reference.wav")
print(res["text"])
PY

# 2. クローン用 semantic token を生成
uv run python fish_speech/models/text2semantic/inference.py \
  --text '読み上げたいテキスト' \
  --prompt-text '参照音声の書き起こしテキスト' \
  --prompt-audio path/to/reference.wav \
  --output-dir output/clone \
  --device cuda

# 3. wav に変換
uv run python fish_speech/models/dac/inference.py \
  -i output/clone/codes_0.npy \
  -o output/clone/clone.wav \
  --checkpoint-path checkpoints/s2-pro/codec.pth \
  -d cuda

#!/usr/bin/env python3
from __future__ import annotations

import argparse
import sys
from pathlib import Path

import torchaudio


def main() -> int:
    p = argparse.ArgumentParser()
    p.add_argument("--text", default="こんにちは。CosyVoiceのテストです。")
    p.add_argument("--out", default="outputs/cosyvoice.wav")
    p.add_argument("--model", default="pretrained_models/CosyVoice2-0.5B")
    p.add_argument("--prompt-text", default="希望你以后能够做的比我还好呦。")
    p.add_argument("--prompt-wav", required=True)
    args = p.parse_args()

    vendor = Path(__file__).resolve().parents[1] / "vendors" / "cosyvoice"
    sys.path.insert(0, str(vendor))
    sys.path.insert(0, str(vendor / "third_party" / "Matcha-TTS"))
    from cosyvoice.cli.cosyvoice import AutoModel

    model = AutoModel(model_dir=args.model)
    out = Path(args.out)
    out.parent.mkdir(parents=True, exist_ok=True)
    for i, chunk in enumerate(model.inference_zero_shot(args.text, args.prompt_text, args.prompt_wav, stream=False)):
        torchaudio.save(str(out), chunk["tts_speech"], model.sample_rate)
        if i == 0:
            break
    print(out)
    return 0


if __name__ == "__main__":
    raise SystemExit(main())

#!/usr/bin/env python3
from __future__ import annotations

import argparse
import sys
from pathlib import Path


def main() -> int:
    p = argparse.ArgumentParser()
    p.add_argument("--text", default="こんにちは。IndexTTSのテストです。")
    p.add_argument("--out", default="outputs/index_tts.wav")
    p.add_argument("--model-dir", default="checkpoints")
    p.add_argument("--prompt-wav", required=True)
    p.add_argument("--device", default="cuda")
    p.add_argument("--emo", default="")   # 感情ベクトルまたは自然言語テキスト
    args = p.parse_args()

    vendor = Path(__file__).resolve().parents[1] / "vendors" / "index-tts"
    model_dir = Path(args.model_dir)
    if not model_dir.is_absolute():
        model_dir = (Path.cwd() / model_dir).resolve()
    cfg_path = model_dir / "config.yaml"

    sys.path.insert(0, str(vendor))
    sys.path.insert(0, str(vendor / "indextts"))
    from indextts.infer_v2 import IndexTTS2

    tts = IndexTTS2(
        model_dir=str(model_dir),
        cfg_path=str(cfg_path),
        use_fp16=args.device.startswith("cuda"),
        device=args.device,
    )
    out = Path(args.out)
    out.parent.mkdir(parents=True, exist_ok=True)
    tts.infer(
        spk_audio_prompt=args.prompt_wav,
        text=args.text,
        output_path=str(out),
        emo_vector=args.emo or None,
    )
    print(out)
    return 0


if __name__ == "__main__":
    raise SystemExit(main())