Skip to content

利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

feat(tts): add VoxCPM provider

lottshin3d19075f93b3
diff --git a/README-en.md b/README-en.md
index d1b845ac..69d593fe 100644
--- a/README-en.md
+++ b/README-en.md
@@ -174,7 +174,7 @@ Thanks to [Kimi](https://platform.kimi.ai?track_id=track-f6b0a640d35c41deb03b247
### Voiceover, Subtitles, and Background Music
- [x] Choose automatic voiceover, uploaded audio, or no voiceover, with voice samples and full narration previews
-- [x] Use **Edge TTS (free, no API key required)**, Azure Speech, SiliconFlow, Google Gemini, Xiaomi MiMo, MiniMax, ElevenLabs, Chatterbox, Kokoro, Fish Audio, and other voice services
+- [x] Use **Edge TTS (free, no API key required)**, Azure Speech, SiliconFlow, Google Gemini, Xiaomi MiMo, MiniMax, ElevenLabs, Chatterbox, Kokoro, Fish Audio, ModelBest VoxCPM, and other voice services
- [x] Generate subtitles and configure their font, position, color, size, outline, and background style
- [x] Use random, local, or AI-generated background music with independent volume control
@@ -436,10 +436,12 @@ The summary contains `total`, `succeeded`, `failed`, and `tasks`; each task entr
### Voice Synthesis
-**Azure TTS V1** in the WebUI is powered by **Edge TTS** and is free to use without an API key. MoneyPrinterTurbo also supports **Azure TTS V2**, **SiliconFlow TTS**, **Google Gemini TTS**, **Xiaomi MiMo TTS**, **ElevenLabs TTS**, self-hosted **Chatterbox TTS**, self-hosted **Kokoro TTS**, **Fish Audio TTS**, and a no-voice mode.
+**Azure TTS V1** in the WebUI is powered by **Edge TTS** and is free to use without an API key. MoneyPrinterTurbo also supports **Azure TTS V2**, **SiliconFlow TTS**, **Google Gemini TTS**, **Xiaomi MiMo TTS**, **MiniMax TTS**, **ElevenLabs TTS**, self-hosted **Chatterbox TTS**, self-hosted **Kokoro TTS**, **Fish Audio TTS**, [ModelBest VoxCPM TTS](https://platform.modelbest.cn/console/docs/api/audio), and a no-voice mode.
Select a provider and voice in the WebUI, then follow the on-screen instructions for any required credentials. Edge TTS does not require an API key; [Azure TTS V2](https://portal.azure.com/) and other cloud providers require credentials from their respective platforms. See the available Edge TTS voices in the [voice list](./docs/voice-list.txt).
+ModelBest VoxCPM requires an API key and a model ID with the `speech_synthesis` capability. Its SSE response streams WAV audio, which MoneyPrinterTurbo automatically converts to the MP3 used by the video pipeline. This integration supports standard text-to-speech with the default voice; reference-audio voice cloning is not included yet.
+
### Subtitle Generation
Two subtitle generation modes are available:
diff --git a/README.md b/README.md
index 3f2335df..4056cbc9 100644
--- a/README.md
+++ b/README.md
@@ -174,7 +174,7 @@
### 配音、字幕与配乐
- [x] 支持自动配音、上传配音和无配音三种方式,并提供音色试听与完整配音预览
-- [x] 集成 **Edge TTS(免费、无需 API Key)**、Azure Speech、SiliconFlow、Google Gemini、小米 MiMo、MiniMax、ElevenLabs、Chatterbox、Kokoro 和 Fish Audio 等配音服务
+- [x] 集成 **Edge TTS(免费、无需 API Key)**、Azure Speech、SiliconFlow、Google Gemini、小米 MiMo、MiniMax、ElevenLabs、Chatterbox、Kokoro、Fish Audio 和 ModelBest VoxCPM 等配音服务
- [x] 支持自动生成字幕,可调整字体、位置、颜色、大小、描边和背景样式
- [x] 支持随机、本地及 AI 生成背景音乐,并可独立控制音量
@@ -423,10 +423,12 @@ JSON 汇总。清单中的相对自定义音频与本地素材路径以清单目
### 语音合成
-WebUI 中的 **Azure TTS V1** 基于 **Edge TTS**,免费且无需 API Key。项目同时支持 **Azure TTS V2**、**SiliconFlow TTS**、**Google Gemini TTS**、**小米 MiMo TTS**、**ElevenLabs TTS**、自托管 **Chatterbox TTS**、自托管 **Kokoro TTS**、**Fish Audio TTS**,以及无配音模式。
+WebUI 中的 **Azure TTS V1** 基于 **Edge TTS**,免费且无需 API Key。项目同时支持 **Azure TTS V2**、**SiliconFlow TTS**、**Google Gemini TTS**、**小米 MiMo TTS**、**MiniMax TTS**、**ElevenLabs TTS**、自托管 **Chatterbox TTS**、自托管 **Kokoro TTS**、**Fish Audio TTS**、[ModelBest VoxCPM TTS](https://platform.modelbest.cn/console/docs/api/audio),以及无配音模式。
可直接在 WebUI 中选择 Provider 和音色,并按照界面提示填写所需凭据。Edge TTS 不需要 API Key;[Azure TTS V2](https://portal.azure.com/) 及其他云端服务需要对应平台的凭据。Edge TTS 音色可查看:[音色列表](./docs/voice-list.txt)。
+ModelBest VoxCPM 需要填写 API Key 和支持 `speech_synthesis` 的模型 ID。服务以 SSE 返回 WAV 音频,项目会自动转换为视频流水线使用的 MP3。当前接入支持普通文本合成和默认音色;参考音频复刻尚未包含。
+
### 字幕生成
当前支持两种字幕生成方式:
diff --git a/app/config/config.py b/app/config/config.py
index d9f62ed4..95452d20 100644
--- a/app/config/config.py
+++ b/app/config/config.py
@@ -499,6 +499,7 @@ def save_config():
config_to_save["chatterbox"] = dict(chatterbox)
config_to_save["kokoro"] = dict(kokoro)
config_to_save["fish_audio"] = dict(fish_audio)
+ config_to_save["voxcpm"] = dict(voxcpm)
config_to_save["ui"] = dict(ui)
serialized_config = toml.dumps(config_to_save)
@@ -556,6 +557,7 @@ elevenlabs = _SynchronizedConfig(_cfg.get("elevenlabs", {}))
chatterbox = _SynchronizedConfig(_cfg.get("chatterbox", {}))
kokoro = _SynchronizedConfig(_cfg.get("kokoro", {}))
fish_audio = _SynchronizedConfig(_cfg.get("fish_audio", {}))
+voxcpm = _SynchronizedConfig(_cfg.get("voxcpm", {}))
ui = _SynchronizedConfig(
_cfg.get(
"ui",
diff --git a/app/services/voice.py b/app/services/voice.py
index 2da26ffe..c317f732 100644
--- a/app/services/voice.py
+++ b/app/services/voice.py
@@ -75,6 +75,8 @@ GEMINI_TTS_VOICES = (
("Sulafat", "Warm"),
)
_MINIMAX_TTS_MAX_AUDIO_HEX_CHARS = 100 * 1024 * 1024
+VOXCPM_DEFAULT_BASE_URL = "https://api.modelbest.cn/v1"
+VOXCPM_DEFAULT_VOICE = "default"
NO_VOICE_NAME = "no-voice"
# `none` 是 PR #981 里曾使用过的无配音标识。这里短期兼容这个值,避免
# 已经手动调用过该分支的 API 用户升级后立即失效;WebUI 和新代码统一使用
@@ -312,6 +314,22 @@ def get_fish_audio_voices() -> list[str]:
return result
+def get_voxcpm_voices(voice_id: str | None = None) -> list[str]:
+ """Return the ModelBest VoxCPM voice selected in the local configuration.
+
+ ModelBest accepts ``default`` when no explicit voice is selected. Voice
+ design is expressed in the input text and voice cloning requires a separate
+ reference-audio workflow, so the first integration deliberately keeps the
+ standard TTS selector to one configured voice id.
+ """
+ voice_id = str(
+ voice_id
+ or config.voxcpm.get("voice_id", VOXCPM_DEFAULT_VOICE)
+ or VOXCPM_DEFAULT_VOICE
+ ).strip()
+ return [f"voxcpm:{voice_id}"]
+
+
_AZURE_VOICES_DATA_FILE = os.path.join(
os.path.dirname(__file__), "data", "azure_voices.json"
)
@@ -412,6 +430,10 @@ def is_fish_audio_voice(voice_name: str) -> bool:
return (voice_name or "").startswith("fish_audio:")
+def is_voxcpm_voice(voice_name: str | None) -> bool:
+ return (voice_name or "").startswith("voxcpm:")
+
+
def get_fish_audio_api_key() -> str:
configured_key = str(config.fish_audio.get("api_key", "") if hasattr(config, "fish_audio") and isinstance(config.fish_audio, dict) else "").strip()
return configured_key or os.getenv("FISH_API_KEY", "").strip()
@@ -458,6 +480,8 @@ def is_azure_v1_voice(voice_name: str | None) -> bool:
return False
if is_fish_audio_voice(name):
return False
+ if is_voxcpm_voice(name):
+ return False
return True
@@ -672,6 +696,12 @@ def _single_tts(
if reference_id == "default":
reference_id = None
return fish_audio_tts(text, voice_file, voice_rate, voice_volume, reference_id=reference_id)
+ elif is_voxcpm_voice(voice_name):
+ voice_id = voice_name.split(":", 1)[1].strip()
+ if voice_id:
+ return voxcpm_tts(text, voice_id, voice_file, voice_rate, voice_volume)
+ logger.error(f"Invalid VoxCPM voice name format: {voice_name}")
+ return None
return azure_tts_v1(text, voice_name, voice_rate, voice_file)
@@ -2401,6 +2431,169 @@ def fish_audio_tts(
return None
+def _iter_voxcpm_sse_events(response):
+ """Yield JSON payloads from ModelBest's Server-Sent Event stream."""
+ event_data = []
+ for raw_line in response.iter_lines(decode_unicode=True):
+ line = raw_line.decode("utf-8") if isinstance(raw_line, bytes) else raw_line
+ if not line:
+ if event_data:
+ try:
+ yield json.loads("\n".join(event_data))
+ except (TypeError, ValueError) as exc:
+ raise ValueError("VoxCPM returned invalid SSE event data") from exc
+ event_data = []
+ continue
+ if line.startswith("data:"):
+ event_data.append(line.removeprefix("data:").strip())
+ if event_data:
+ try:
+ yield json.loads("\n".join(event_data))
+ except (TypeError, ValueError) as exc:
+ raise ValueError("VoxCPM returned invalid trailing SSE event data") from exc
+
+
+def voxcpm_tts(
+ text: str,
+ voice_id: str,
+ voice_file: str,
+ voice_rate: float = 1.0,
+ voice_volume: float = 1.0,
+) -> Union[SubMaker, None]:
+ """Generate speech through ModelBest's VoxCPM Audio Speech API.
+
+ ModelBest always streams Base64-encoded WAV chunks through SSE. The
+ assembled WAV is decoded and exported to the project's requested output
+ format so that the regular subtitle and video paths remain unchanged.
+ ModelBest does not define a numeric speed field, so ``voice_rate`` is not
+ sent. ``voice_volume`` is applied later by MoneyPrinterTurbo's video mixer.
+ """
+ from pydub import AudioSegment
+
+ text = (text or "").strip()
+ if not text:
+ logger.error("VoxCPM TTS text is empty")
+ return None
+
+ api_key = str(config.voxcpm.get("api_key", "") or "").strip()
+ if not api_key:
+ logger.error("VoxCPM API key is not set")
+ return None
+
+ base_url = str(
+ config.voxcpm.get("base_url", VOXCPM_DEFAULT_BASE_URL)
+ or VOXCPM_DEFAULT_BASE_URL
+ ).strip().rstrip("/")
+ model_id = str(config.voxcpm.get("model_id", "") or "").strip()
+ if not model_id:
+ logger.error("VoxCPM model ID is not set")
+ return None
+ voice_id = str(voice_id or VOXCPM_DEFAULT_VOICE).strip() or VOXCPM_DEFAULT_VOICE
+
+ url = f"{base_url}/audio/speech"
+ headers = {
+ "Authorization": f"Bearer {api_key}",
+ "Content-Type": "application/json",
+ "Accept": "text/event-stream",
+ }
+ payload = {
+ "model": model_id,
+ "input": text,
+ "voice": voice_id,
+ "response_format": "wav",
+ "stream": True,
+ }
+ _configure_pydub_ffmpeg(AudioSegment)
+
+ for attempt in range(3):
+ temporary_audio = None
+ response = None
+ try:
+ logger.info(
+ f"start VoxCPM TTS, model: {model_id}, voice: {voice_id}, "
+ f"try: {attempt + 1}"
+ )
+ response = requests.post(
+ url,
+ json=payload,
+ headers=headers,
+ stream=True,
+ timeout=(10, 120),
+ )
+ if response.status_code != 200:
+ logger.error(
+ f"VoxCPM TTS failed with status {response.status_code}: "
+ f"{response.text[:200]}"
+ )
+ continue
+
+ audio_chunks = []
+ completed = False
+ for event in _iter_voxcpm_sse_events(response):
+ event_type = event.get("type")
+ if event_type == "speech.audio.delta":
+ encoded_chunk = event.get("audio")
+ if not isinstance(encoded_chunk, str) or not encoded_chunk:
+ raise ValueError("VoxCPM returned an empty audio chunk")
+ try:
+ audio_chunks.append(base64.b64decode(encoded_chunk, validate=True))
+ except (ValueError, TypeError) as exc:
+ raise ValueError("VoxCPM returned invalid Base64 audio") from exc
+ elif event_type == "speech.audio.done":
+ completed = True
+ break
+
+ if not completed:
+ raise ValueError("VoxCPM stream ended before speech.audio.done")
+ audio_bytes = b"".join(audio_chunks)
+ if not audio_bytes:
+ raise ValueError("VoxCPM returned no audio data")
+
+ audio_segment = AudioSegment.from_file(io.BytesIO(audio_bytes), format="wav")
+ if len(audio_segment) <= 0:
+ raise ValueError("VoxCPM returned an empty WAV")
+
+ ensure_file_path_exists(voice_file)
+ output_format = utils.parse_extension(voice_file) or "mp3"
+ with tempfile.NamedTemporaryFile(
+ dir=os.path.dirname(os.path.abspath(voice_file)),
+ suffix=f".{output_format}",
+ delete=False,
+ ) as output:
+ temporary_audio = output.name
+ audio_segment.export(temporary_audio, format=output_format)
+
+ audio_clip = AudioFileClip(temporary_audio)
+ try:
+ audio_duration = audio_clip.duration
+ finally:
+ audio_clip.close()
+ if not math.isfinite(audio_duration) or audio_duration <= 0:
+ raise ValueError("VoxCPM produced an invalid audio duration")
+
+ sub_maker = ensure_legacy_submaker_fields(SubMaker())
+ os.replace(temporary_audio, voice_file)
+ logger.success(f"VoxCPM TTS succeeded: {voice_file}")
+ return populate_legacy_submaker_with_full_text(
+ sub_maker=sub_maker,
+ text=text,
+ audio_duration_seconds=audio_duration,
+ )
+ except Exception as exc:
+ logger.error(f"VoxCPM TTS failed: {exc}")
+ finally:
+ close_response = getattr(response, "close", None)
+ if callable(close_response):
+ close_response()
+ if temporary_audio and os.path.exists(temporary_audio):
+ try:
+ os.unlink(temporary_audio)
+ except OSError as exc:
+ logger.warning(f"could not remove temporary VoxCPM audio: {exc}")
+
+ return None
+
+
def _format_text(text: str) -> str:
"""
清理字幕对齐前的脚本文本。
diff --git a/config.example.toml b/config.example.toml
index 72ce4e8f..58e7c5a5 100644
--- a/config.example.toml
+++ b/config.example.toml
@@ -569,6 +569,16 @@ voices = []
# windows (e.g. through August 2026). There is no SLA. Please check
# https://fish.audio/pricing for current availability and commercial terms.
+[voxcpm]
+# ModelBest VoxCPM cloud TTS. Create an API Key and select a model with the
+# `speech_synthesis` capability at https://platform.modelbest.cn/console/
+# The Audio Speech API returns a streaming WAV response; MoneyPrinterTurbo
+# converts it to its internal MP3 voiceover format automatically.
+base_url = "https://api.modelbest.cn/v1"
+api_key = ""
+model_id = ""
+voice_id = "default"
+
# =============================================================================
# WebUI Preferences / WebUI 偏好
# =============================================================================
diff --git a/test/services/test_config.py b/test/services/test_config.py
index 2a165b1b..343a36ff 100644
--- a/test/services/test_config.py
+++ b/test/services/test_config.py
@@ -63,6 +63,12 @@ class TestConfigPersistence:
assert "loomloom_market_listing_id" not in app_config
assert "loomloom_video_market_listing_id" not in app_config
assert app_config["shengsuanyun_api_key"] == ""
+ assert example_config["voxcpm"] == {
+ "base_url": "https://api.modelbest.cn/v1",
+ "api_key": "",
+ "model_id": "",
+ "voice_id": "default",
+ }
assert example_config["whisper"]["device"] == "cpu"
def test_example_config_covers_llm_provider_registry(self):
diff --git a/test/services/test_voxcpm.py b/test/services/test_voxcpm.py
new file mode 100644
index 00000000..7c66d0d9
--- /dev/null
+++ b/test/services/test_voxcpm.py
@@ -0,0 +1,170 @@
+"""ModelBest VoxCPM provider tests without external credentials or network access."""
+
+import base64
+import json
+from pathlib import Path
+from types import SimpleNamespace
+from unittest.mock import Mock
+
+import pytest
+
+from app.config import config
+from app.services import voice
+
+
+class _FakeSegment:
+ def __init__(self, duration_ms=1600):
+ self.duration_ms = duration_ms
+
+ def __len__(self):
+ return self.duration_ms
+
+ def export(self, target, format):
+ assert format == "mp3"
+ Path(target).write_bytes(b"encoded-mp3")
+
+
+def _sse_event(event_type, **payload):
+ return f"data: {json.dumps({'type': event_type, **payload})}"
+
+
+def _sse_lines(*events):
+ lines = []
+ for event in events:
+ lines.extend([event, ""])
+ return lines
+
+
+def voxcpm_config(monkeypatch):
+ settings = {
+ "api_key": "test-key",
+ "base_url": "https://api.modelbest.cn/v1/",
+ "model_id": "voxcpm-tts-test",
+ "voice_id": "default",
+ }
+ monkeypatch.setattr(config, "voxcpm", settings)
+ return settings
+
+
+def test_voice_helpers_and_dispatch():
+ assert voice.get_voxcpm_voices("default") == ["voxcpm:default"]
+ assert voice.is_voxcpm_voice("voxcpm:default")
+ assert not voice.is_voxcpm_voice("fish_audio:default")
+ assert not voice.is_azure_v1_voice("voxcpm:default")
+
+ sentinel = object()
+ with pytest.MonkeyPatch.context() as monkeypatch:
+ implementation = Mock(return_value=sentinel)
+ monkeypatch.setattr(voice, "voxcpm_tts", implementation)
+ result = voice.tts("hello", "voxcpm:default", 1.2, "out.mp3", 0.8)
+
+ assert result is sentinel
+ implementation.assert_called_once_with("hello", "default", "out.mp3", 1.2, 0.8)
+
+
+def test_voxcpm_tts_assembles_sse_wav_and_converts_to_mp3(
+ monkeypatch, tmp_path, voxcpm_config
+):
+ audio_chunks = [b"RIFF", b"WAVE"]
+ response = SimpleNamespace(
+ status_code=200,
+ text="",
+ iter_lines=lambda decode_unicode: _sse_lines(
+ _sse_event("speech.audio.delta", audio=base64.b64encode(audio_chunks[0]).decode()),
+ _sse_event("speech.audio.delta", audio=base64.b64encode(audio_chunks[1]).decode()),
+ _sse_event("speech.audio.done", usage={"total_tokens": 1}),
+ ),
+ close=Mock(),
+ )
+ post = Mock(return_value=response)
+ monkeypatch.setattr(voice.requests, "post", post)
+
+ captured = {}
+
+ def from_file(source, format):
+ captured["source"] = source.read()
+ captured["format"] = format
+ return _FakeSegment()
+
+ monkeypatch.setattr("pydub.AudioSegment.from_file", from_file)
+ monkeypatch.setattr(voice, "AudioFileClip", Mock(return_value=SimpleNamespace(
+ duration=1.6, close=lambda: None
+ )))
+
+ output = tmp_path / "voice.mp3"
+ maker = voice.voxcpm_tts("Hello VoxCPM.", "default", str(output))
+
+ assert maker is not None
+ assert output.read_bytes() == b"encoded-mp3"
+ assert captured == {"source": b"".join(audio_chunks), "format": "wav"}
+ assert getattr(maker, "subs", []) == ["Hello VoxCPM"]
+ assert post.call_args.kwargs["json"] == {
+ "model": "voxcpm-tts-test",
+ "input": "Hello VoxCPM.",
+ "voice": "default",
+ "response_format": "wav",
+ "stream": True,
+ }
+ assert post.call_args.kwargs["headers"]["Authorization"] == "Bearer test-key"
+ assert post.call_args.kwargs["headers"]["Accept"] == "text/event-stream"
+ assert post.call_args.kwargs["stream"] is True
+ assert post.call_args.kwargs["timeout"] == (10, 120)
+ response.close.assert_called_once()
+
+
+ "events",
+ [
+ _sse_lines(_sse_event("speech.audio.done")),
+ _sse_lines(_sse_event("speech.audio.delta", audio="not base64")),
+ _sse_lines(_sse_event("speech.audio.delta", audio=base64.b64encode(b"audio").decode())),
+ ["data: {invalid json}", ""],
+ ],
+)
+def test_voxcpm_tts_failure_never_overwrites_existing_audio(
+ monkeypatch, tmp_path, voxcpm_config, events
+):
+ response = SimpleNamespace(
+ status_code=200,
+ text="",
+ iter_lines=lambda decode_unicode: events,
+ close=lambda: None,
+ )
+ post = Mock(return_value=response)
+ monkeypatch.setattr(voice.requests, "post", post)
+ output = tmp_path / "existing.mp3"
+ output.write_bytes(b"previous-audio")
+
+ assert voice.voxcpm_tts("Hello", "default", str(output)) is None
+ assert output.read_bytes() == b"previous-audio"
+ assert post.call_count == 3
+
+
+def test_voxcpm_requires_key_and_model_without_making_requests(monkeypatch, tmp_path):
+ post = Mock()
+ monkeypatch.setattr(voice.requests, "post", post)
+ monkeypatch.setattr(config, "voxcpm", {"api_key": "", "model_id": "model"})
+ assert voice.voxcpm_tts("Hello", "default", str(tmp_path / "voice.mp3")) is None
+
+ monkeypatch.setattr(config, "voxcpm", {"api_key": "key", "model_id": ""})
+ assert voice.voxcpm_tts("Hello", "default", str(tmp_path / "voice.mp3")) is None
+ post.assert_not_called()
+
+
+def test_voxcpm_http_error_is_retried_and_preserves_output(
+ monkeypatch, tmp_path, voxcpm_config
+):
+ response = SimpleNamespace(
+ status_code=503,
+ text="temporarily unavailable",
+ close=lambda: None,
+ )
+ post = Mock(return_value=response)
+ monkeypatch.setattr(voice.requests, "post", post)
+ output = tmp_path / "existing.mp3"
+ output.write_bytes(b"previous-audio")
+
+ assert voice.voxcpm_tts("Hello", "default", str(output)) is None
+ assert output.read_bytes() == b"previous-audio"
+ assert post.call_count == 3
diff --git a/test/services/test_webui_tts_settings.py b/test/services/test_webui_tts_settings.py
index 3c9de67f..76239b64 100644
--- a/test/services/test_webui_tts_settings.py
+++ b/test/services/test_webui_tts_settings.py
@@ -24,6 +24,7 @@ TTS_API_KEY_LABELS = {
"MiniMax TTS API Key": "platform.minimaxi.com",
"ElevenLabs API Key": "elevenlabs.io/app/settings/api-keys",
"Chatterbox API Key": "github.com/travisvn/chatterbox-tts-api",
+ "VoxCPM API Key": "platform.modelbest.cn/console/keys",
}
TTS_PROVIDER_WIDGETS = {
@@ -34,6 +35,7 @@ TTS_PROVIDER_WIDGETS = {
"minimax-tts": ("minimax_tts_api_key_input", "MiniMax TTS API Key"),
"elevenlabs": ("elevenlabs_api_key_input", "ElevenLabs API Key"),
"chatterbox": ("chatterbox_api_key_input", "Chatterbox API Key"),
+ "voxcpm": ("voxcpm_api_key_input", "VoxCPM API Key"),
}
@@ -99,6 +101,40 @@ def test_tts_provider_inputs_render_the_standardized_labels():
assert [str(item.value) for item in app.exception] == []
+def test_voxcpm_settings_render_model_and_endpoint_fields():
+ test_config = dict(
+ config.voxcpm,
+ api_key="",
+ model_id="speech-model",
+ base_url=voice.VOXCPM_DEFAULT_BASE_URL,
+ voice_id=voice.VOXCPM_DEFAULT_VOICE,
+ )
+ test_ui = dict(
+ config.ui,
+ voice_mode="tts",
+ tts_server="voxcpm",
+ voice_name="voxcpm:default",
+ )
+
+ with (
+ patch.object(config, "voxcpm", test_config),
+ patch.object(config, "ui", test_ui),
+ patch.object(config, "try_save_config", return_value=True),
+ ):
+ app = AppTest.from_file(str(WEBUI_MAIN), default_timeout=30)
+ app.session_state["ui_language"] = "en"
+ app.run()
+
+ api_key_input = _widget_by_key(app.text_input, "voxcpm_api_key_input")
+ assert api_key_input.proto.type == api_key_input.proto.PASSWORD
+ assert _widget_by_key(app.text_input, "voxcpm_model_id_input").value == "speech-model"
+ assert (
+ _widget_by_key(app.text_input, "voxcpm_base_url_input").value
+ == voice.VOXCPM_DEFAULT_BASE_URL
+ )
+ assert [str(item.value) for item in app.exception] == []
+
+
def test_elevenlabs_reconnect_restores_saved_key_before_loading_voices():
"""
服务重启后浏览器可能重放空密码状态;WebUI 应保留配置并在当前 rerun 就用
diff --git a/test/services/test_webui_voice_preview.py b/test/services/test_webui_voice_preview.py
index f1b858ef..1ff7c614 100644
--- a/test/services/test_webui_voice_preview.py
+++ b/test/services/test_webui_voice_preview.py
@@ -91,6 +91,12 @@ def test_provider_signature_changes_when_api_key_changes():
"base_url": "http://127.0.0.1:4123/v1",
"model_id": "chatterbox",
},
+ voxcpm={
+ "api_key": "old-voxcpm",
+ "base_url": "https://api.modelbest.cn/v1",
+ "model_id": "speech-model",
+ "voice_id": "default",
+ },
)
provider_signature = _load_provider_signature(test_config)
@@ -103,6 +109,29 @@ def test_provider_signature_changes_when_api_key_changes():
assert "new-elevenlabs" not in str(new_signature)
+def test_voxcpm_preview_signature_tracks_endpoint_model_and_credentials():
+ test_config = SimpleNamespace(
+ app={}, azure={}, siliconflow={}, elevenlabs={}, chatterbox={}, kokoro={},
+ voxcpm={
+ "api_key": "old-key",
+ "base_url": "https://api.modelbest.cn/v1",
+ "model_id": "speech-model-a",
+ "voice_id": "default",
+ },
+ )
+ provider_signature = _load_provider_signature(test_config)
+
+ original = provider_signature("voxcpm")
+ test_config.voxcpm["model_id"] = "speech-model-b"
+ changed_model = provider_signature("voxcpm")
+ test_config.voxcpm["api_key"] = "new-key"
+ changed_key = provider_signature("voxcpm")
+
+ assert original != changed_model != changed_key
+ assert "old-key" not in str(original)
+ assert "new-key" not in str(changed_key)
+
+
def test_full_voiceover_preview_is_disabled_until_script_exists():
"""完整预览必须由用户主动触发,文案为空时不能误调用商业 TTS。"""
test_ui = dict(
diff --git a/webui/Main.py b/webui/Main.py
index a827d033..fb677e49 100644
--- a/webui/Main.py
+++ b/webui/Main.py
@@ -101,6 +101,8 @@ DEFAULT_KOKORO_BASE_URL = "http://127.0.0.1:8880/v1"
DEFAULT_KOKORO_MODEL = "kokoro"
# empty = ask the server for its voice list (GET {base_url}/audio/voices)
DEFAULT_KOKORO_VOICES: list[str] = []
+DEFAULT_VOXCPM_BASE_URL = voice.VOXCPM_DEFAULT_BASE_URL
+DEFAULT_VOXCPM_VOICE = voice.VOXCPM_DEFAULT_VOICE
ONBOARDING_TOUR_KEY = "mpt-onboarding-v1"
CUSTOM_LLM_ENDPOINT_ID = "custom"
VOICE_MODE_TTS = "tts"
@@ -224,6 +226,7 @@ _RUNTIME_CONFIG_SECTIONS = {
"minimax_tts": config.minimax_tts,
"siliconflow": config.siliconflow,
"fish_audio": config.fish_audio,
+ "voxcpm": config.voxcpm,
"ui": config.ui,
}
# 设置预设与密钥备份使用各自的文件标识。导入时先校验 schema 和版本,
@@ -1402,6 +1405,8 @@ def _infer_tts_server_from_voice(voice_name):
return "kokoro"
if voice.is_fish_audio_voice(voice_name):
return "fish_audio"
+ if voice.is_voxcpm_voice(voice_name):
+ return "voxcpm"
if voice.is_azure_v2_voice(voice_name):
return "azure-tts-v2"
return "azure-tts-v1"
@@ -5486,6 +5491,13 @@ def _get_voice_preview_provider_signature(tts_server: str) -> dict:
"model_id": config.kokoro.get("model_id", ""),
"credential": _credential_signature(config.kokoro.get("api_key", "")),
}
+ if tts_server == "voxcpm":
+ return {
+ "base_url": config.voxcpm.get("base_url", ""),
+ "model_id": config.voxcpm.get("model_id", ""),
+ "voice_id": config.voxcpm.get("voice_id", "default"),
+ "credential": _credential_signature(config.voxcpm.get("api_key", "")),
+ }
return {}
@@ -6329,6 +6341,7 @@ def _render_audio_settings(panel, params):
("chatterbox", "Chatterbox TTS"),
("kokoro", "Kokoro TTS"),
("fish_audio", "Fish Audio TTS"),
+ ("voxcpm", "VoxCPM TTS"),
]
tts_server_values = [server_value for server_value, _ in tts_servers]
@@ -6404,6 +6417,8 @@ def _render_audio_settings(panel, params):
filtered_voices = _get_kokoro_voice_options(saved_voice_name)
elif selected_tts_server == "fish_audio":
filtered_voices = voice.get_fish_audio_voices()
+ elif selected_tts_server == "voxcpm":
+ filtered_voices = voice.get_voxcpm_voices()
else:
# 获取Azure的声音列表
all_voices = voice.get_all_azure_voices(filter_locals=None)
@@ -6437,6 +6452,8 @@ def _render_audio_settings(panel, params):
display_name.replace("Female", tr("Female"))
.replace("Male", tr("Male"))
)
+ if voice.is_voxcpm_voice(v):
+ return v.split(":", 1)[1] or DEFAULT_VOXCPM_VOICE
return (
v.replace("Female", tr("Female"))
.replace("Male", tr("Male"))
@@ -6658,6 +6675,42 @@ def _render_audio_settings(panel, params):
)
_set_runtime_config("fish_audio", "model", fish_model)
+ # ModelBest hosts VoxCPM behind its streaming Audio Speech API.
+ # The fixed provider endpoint is still editable for compatible
+ # gateways, while the user only has to supply an API key and a
+ # speech_synthesis-capable model id for the standard platform.
+ if tts_mode_enabled and (
+ selected_tts_server == "voxcpm"
+ or (voice_name and voice.is_voxcpm_voice(voice_name))
+ ):
+ voxcpm_api_key = st.text_input(
+ tr("VoxCPM API Key"),
+ value=config.voxcpm.get("api_key", ""),
+ type="password",
+ key="voxcpm_api_key_input",
+ )
+ _set_runtime_config("voxcpm", "api_key", voxcpm_api_key)
+
+ voxcpm_model = st.text_input(
+ tr("VoxCPM Model ID"),
+ value=config.voxcpm.get("model_id", ""),
+ key="voxcpm_model_id_input",
+ placeholder=tr("VoxCPM Model ID Placeholder"),
+ )
+ _set_runtime_config("voxcpm", "model_id", voxcpm_model.strip())
+
+ voxcpm_base_url = st.text_input(
+ tr("VoxCPM Base URL"),
+ value=config.voxcpm.get("base_url") or DEFAULT_VOXCPM_BASE_URL,
+ key="voxcpm_base_url_input",
+ placeholder=DEFAULT_VOXCPM_BASE_URL,
+ )
+ _set_runtime_config(
+ "voxcpm",
+ "base_url",
+ (voxcpm_base_url or DEFAULT_VOXCPM_BASE_URL).strip().rstrip("/"),
+ )
+
# Chatterbox API settings section (self-hosted, OpenAI-compatible)
if tts_mode_enabled and (
selected_tts_server == "chatterbox"
diff --git a/webui/i18n/az.json b/webui/i18n/az.json
index 81e14bb9..21018c54 100644
--- a/webui/i18n/az.json
+++ b/webui/i18n/az.json
@@ -256,6 +256,10 @@
"ElevenLabs API Key": "ElevenLabs API açarı ([API açarını al](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "ElevenLabs modeli",
"Fish Audio API Key": "Fish Audio API açarı ([API açarını al](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "ModelBest API açarı ([API açarını al](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "VoxCPM model ID",
+ "VoxCPM Model ID Placeholder": "ModelBest-də speech_synthesis model ID seçin",
+ "VoxCPM Base URL": "VoxCPM Base URL",
"Fish Audio Model": "Fish Audio modeli",
"Chatterbox Base URL": "Chatterbox əsas URL-i",
"Chatterbox API Key": "Chatterbox API açarı (istəyə bağlı; [Quraşdırmaya bax](https://github.com/travisvn/chatterbox-tts-api))",
diff --git a/webui/i18n/de.json b/webui/i18n/de.json
index 6715469f..46b949e6 100644
--- a/webui/i18n/de.json
+++ b/webui/i18n/de.json
@@ -265,6 +265,10 @@
"ElevenLabs API Key": "ElevenLabs API-Schlüssel ([Schlüssel abrufen](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "ElevenLabs Modell",
"Fish Audio API Key": "Fish Audio API-Schlüssel ([Schlüssel abrufen](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "ModelBest API-Schlüssel ([API-Schlüssel abrufen](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "VoxCPM-Modell-ID",
+ "VoxCPM Model ID Placeholder": "Eine speech_synthesis-Modell-ID in ModelBest auswählen",
+ "VoxCPM Base URL": "VoxCPM-Basis-URL",
"Fish Audio Model": "Fish Audio Modell",
"Chatterbox Base URL": "Chatterbox-Basis-URL",
"Chatterbox API Key": "Chatterbox API-Schlüssel (Optional; [Konfiguration ansehen](https://github.com/travisvn/chatterbox-tts-api))",
diff --git a/webui/i18n/en.json b/webui/i18n/en.json
index 64d7c48a..b47fbdfe 100644
--- a/webui/i18n/en.json
+++ b/webui/i18n/en.json
@@ -275,6 +275,10 @@
"ElevenLabs Model": "ElevenLabs Model",
"Fish Audio API Key": "Fish Audio API Key ([Get API Key](https://fish.audio/app/developers))",
"Fish Audio Model": "Fish Audio Model",
+ "VoxCPM API Key": "ModelBest API Key ([Get API Key](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "VoxCPM Model ID",
+ "VoxCPM Model ID Placeholder": "Select a speech_synthesis model ID in ModelBest",
+ "VoxCPM Base URL": "VoxCPM Base URL",
"Chatterbox Base URL": "Chatterbox Base URL",
"Chatterbox API Key": "Chatterbox API Key (Optional; [View Setup](https://github.com/travisvn/chatterbox-tts-api))",
"Chatterbox Model": "Chatterbox Model",
@@ -296,6 +300,7 @@
"tts_provider_tips.chatterbox": "Self-hosted. Run a compatible [Chatterbox TTS API](https://github.com/travisvn/chatterbox-tts-api), then enter a Base URL ending in `/v1`; the API key is usually optional.",
"tts_provider_tips.kokoro": "Self-hosted and free: run a compatible [Kokoro-FastAPI](https://github.com/remsky/Kokoro-FastAPI) server (Apache-2.0 model, CPU is enough), then enter a Base URL ending in `/v1`; the voice list is read from the server.",
"tts_provider_tips.fish_audio": "Requires a Fish Audio API key from the [developer portal](https://fish.audio/app/developers). [Browse public voices](https://fish.audio) or configure custom voices in `config.toml`. See [pricing & terms](https://fish.audio/pricing).",
+ "tts_provider_tips.voxcpm": "Requires a [ModelBest API Key](https://platform.modelbest.cn/console/keys) and a model ID with the `speech_synthesis` capability. The API streams WAV audio and supports the default voice in this integration. Numeric speed is not supported; describe the desired pace at the start of the script, for example `(slightly faster)`. Reference-audio voice cloning is not included yet.",
"Hide Log": "Hide Log",
"Hide Basic Settings": "Hide Basic Settings\n\nHidden, the basic settings panel will not be displayed on the page.\n\nIf you need to display it again, please set `hide_config = false` in `config.toml`",
"LLM Settings": "**LLM Settings**",
diff --git a/webui/i18n/es.json b/webui/i18n/es.json
index c8df1011..66c5c9e5 100644
--- a/webui/i18n/es.json
+++ b/webui/i18n/es.json
@@ -262,6 +262,10 @@
"ElevenLabs API Key": "Clave API de ElevenLabs ([Obtener clave](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "Modelo de ElevenLabs",
"Fish Audio API Key": "Clave API de Fish Audio ([Obtener clave](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "Clave API de ModelBest ([Obtener clave](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "ID del modelo VoxCPM",
+ "VoxCPM Model ID Placeholder": "Selecciona un ID de modelo speech_synthesis en ModelBest",
+ "VoxCPM Base URL": "URL base de VoxCPM",
"Fish Audio Model": "Modelo Fish Audio",
"Chatterbox API Key": "Clave API de Chatterbox (Opcional; [Ver configuración](https://github.com/travisvn/chatterbox-tts-api))",
"Chatterbox Base URL": "URL base de Chatterbox",
diff --git a/webui/i18n/fr.json b/webui/i18n/fr.json
index d4084989..5a19e589 100644
--- a/webui/i18n/fr.json
+++ b/webui/i18n/fr.json
@@ -262,6 +262,10 @@
"ElevenLabs API Key": "Clé API ElevenLabs ([Obtenir la clé API](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "Modèle ElevenLabs",
"Fish Audio API Key": "Clé API Fish Audio ([Obtenir la clé API](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "Clé API ModelBest ([Obtenir la clé API](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "ID du modèle VoxCPM",
+ "VoxCPM Model ID Placeholder": "Sélectionnez un ID de modèle speech_synthesis dans ModelBest",
+ "VoxCPM Base URL": "URL de base VoxCPM",
"Fish Audio Model": "Modèle Fish Audio",
"Chatterbox Base URL": "URL de base Chatterbox",
"Chatterbox API Key": "Clé API Chatterbox (Optionnel ; [Voir la configuration](https://github.com/travisvn/chatterbox-tts-api))",
diff --git a/webui/i18n/id.json b/webui/i18n/id.json
index 77e69f0c..d84e1887 100644
--- a/webui/i18n/id.json
+++ b/webui/i18n/id.json
@@ -262,6 +262,10 @@
"ElevenLabs API Key": "Kunci API ElevenLabs ([Dapatkan kunci](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "Model ElevenLabs",
"Fish Audio API Key": "Kunci API Fish Audio ([Dapatkan kunci](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "Kunci API ModelBest ([Dapatkan kunci](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "ID Model VoxCPM",
+ "VoxCPM Model ID Placeholder": "Pilih ID model speech_synthesis di ModelBest",
+ "VoxCPM Base URL": "URL Dasar VoxCPM",
"Fish Audio Model": "Model Fish Audio",
"Chatterbox Base URL": "URL Dasar Chatterbox",
"Chatterbox API Key": "Kunci API Chatterbox (Opsional; [Lihat konfigurasi](https://github.com/travisvn/chatterbox-tts-api))",
diff --git a/webui/i18n/it.json b/webui/i18n/it.json
index 4490c327..3f732862 100644
--- a/webui/i18n/it.json
+++ b/webui/i18n/it.json
@@ -262,6 +262,10 @@
"ElevenLabs API Key": "Chiave API ElevenLabs ([Ottieni chiave API](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "Modello ElevenLabs",
"Fish Audio API Key": "Chiave API Fish Audio ([Ottieni chiave API](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "Chiave API ModelBest ([Ottieni chiave API](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "ID modello VoxCPM",
+ "VoxCPM Model ID Placeholder": "Seleziona un ID modello speech_synthesis in ModelBest",
+ "VoxCPM Base URL": "URL base VoxCPM",
"Fish Audio Model": "Modello Fish Audio",
"Chatterbox Base URL": "Base URL di Chatterbox",
"Chatterbox API Key": "Chiave API Chatterbox (facoltativa; [Visualizza configurazione](https://github.com/travisvn/chatterbox-tts-api))",
diff --git a/webui/i18n/ko.json b/webui/i18n/ko.json
index 06c8e988..6b3ffc57 100644
--- a/webui/i18n/ko.json
+++ b/webui/i18n/ko.json
@@ -262,6 +262,10 @@
"ElevenLabs API Key": "ElevenLabs API 키 ([API 키 발급](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "ElevenLabs 모델",
"Fish Audio API Key": "Fish Audio API 키 ([API 키 발급](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "ModelBest API 키 ([API 키 발급](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "VoxCPM 모델 ID",
+ "VoxCPM Model ID Placeholder": "ModelBest에서 speech_synthesis 모델 ID를 선택하세요",
+ "VoxCPM Base URL": "VoxCPM Base URL",
"Fish Audio Model": "Fish Audio 모델",
"Chatterbox Base URL": "Chatterbox Base URL",
"Chatterbox API Key": "Chatterbox API 키 (선택; [설정 방법](https://github.com/travisvn/chatterbox-tts-api))",
diff --git a/webui/i18n/pt.json b/webui/i18n/pt.json
index df0d0418..714a5696 100644
--- a/webui/i18n/pt.json
+++ b/webui/i18n/pt.json
@@ -262,6 +262,10 @@
"ElevenLabs API Key": "Chave API do ElevenLabs ([Obter chave](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "Modelo do ElevenLabs",
"Fish Audio API Key": "Chave API do Fish Audio ([Obter chave](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "Chave API do ModelBest ([Obter chave](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "ID do modelo VoxCPM",
+ "VoxCPM Model ID Placeholder": "Selecione um ID de modelo speech_synthesis no ModelBest",
+ "VoxCPM Base URL": "URL base do VoxCPM",
"Fish Audio Model": "Modelo Fish Audio",
"Chatterbox Base URL": "URL base do Chatterbox",
"Chatterbox API Key": "Chave API do Chatterbox (Opcional; [Ver configuração](https://github.com/travisvn/chatterbox-tts-api))",
diff --git a/webui/i18n/ru.json b/webui/i18n/ru.json
index 97d49753..0f201513 100644
--- a/webui/i18n/ru.json
+++ b/webui/i18n/ru.json
@@ -258,6 +258,10 @@
"ElevenLabs API Key": "API-ключ ElevenLabs ([получить ключ](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "Модель ElevenLabs",
"Fish Audio API Key": "API-ключ Fish Audio ([получить ключ](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "API-ключ ModelBest ([получить ключ](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "ID модели VoxCPM",
+ "VoxCPM Model ID Placeholder": "Выберите ID модели speech_synthesis в ModelBest",
+ "VoxCPM Base URL": "Базовый URL VoxCPM",
"Fish Audio Model": "Модель Fish Audio",
"Chatterbox Base URL": "Базовый URL Chatterbox",
"Chatterbox API Key": "API-ключ Chatterbox (необязательно; [настройка](https://github.com/travisvn/chatterbox-tts-api))",
diff --git a/webui/i18n/tr.json b/webui/i18n/tr.json
index b5daff94..a938097b 100644
--- a/webui/i18n/tr.json
+++ b/webui/i18n/tr.json
@@ -260,6 +260,10 @@
"ElevenLabs API Key": "ElevenLabs API Anahtarı ([Anahtar al](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "ElevenLabs Modeli",
"Fish Audio API Key": "Fish Audio API Anahtarı ([Anahtar al](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "ModelBest API Anahtarı ([Anahtar al](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "VoxCPM Model Kimliği",
+ "VoxCPM Model ID Placeholder": "ModelBest'te bir speech_synthesis model kimliği seçin",
+ "VoxCPM Base URL": "VoxCPM Temel URL",
"Fish Audio Model": "Fish Audio Modeli",
"Chatterbox Base URL": "Chatterbox Temel URL'si",
"Chatterbox API Key": "Chatterbox API Anahtarı (İsteğe bağlı; [Yapılandırmayı görüntüle](https://github.com/travisvn/chatterbox-tts-api))",
diff --git a/webui/i18n/vi.json b/webui/i18n/vi.json
index 9d4298a4..5411822d 100644
--- a/webui/i18n/vi.json
+++ b/webui/i18n/vi.json
@@ -262,6 +262,10 @@
"ElevenLabs API Key": "Khóa API ElevenLabs ([Lấy khóa](https://elevenlabs.io/app/settings/api-keys))",
"ElevenLabs Model": "Mô hình ElevenLabs",
"Fish Audio API Key": "Khóa API Fish Audio ([Lấy khóa](https://fish.audio/app/developers))",
+ "VoxCPM API Key": "Khóa API ModelBest ([Lấy khóa](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "ID mô hình VoxCPM",
+ "VoxCPM Model ID Placeholder": "Chọn ID mô hình speech_synthesis trong ModelBest",
+ "VoxCPM Base URL": "URL cơ sở VoxCPM",
"Fish Audio Model": "Mô hình Fish Audio",
"Chatterbox Base URL": "URL cơ sở Chatterbox",
"Chatterbox API Key": "Khóa API Chatterbox (Không bắt buộc; [Xem cấu hình](https://github.com/travisvn/chatterbox-tts-api))",
diff --git a/webui/i18n/zh.json b/webui/i18n/zh.json
index d789b357..7f4794ec 100644
--- a/webui/i18n/zh.json
+++ b/webui/i18n/zh.json
@@ -275,6 +275,10 @@
"ElevenLabs Model": "ElevenLabs 模型",
"Fish Audio API Key": "Fish Audio API 密钥([点击获取](https://fish.audio/app/developers))",
"Fish Audio Model": "Fish Audio 模型",
+ "VoxCPM API Key": "ModelBest API 密钥([点击获取](https://platform.modelbest.cn/console/keys))",
+ "VoxCPM Model ID": "VoxCPM 模型 ID",
+ "VoxCPM Model ID Placeholder": "在 ModelBest 中选择支持 speech_synthesis 的模型 ID",
+ "VoxCPM Base URL": "VoxCPM Base URL",
"Chatterbox Base URL": "Chatterbox Base URL",
"Chatterbox API Key": "Chatterbox API 密钥(可选,[查看配置](https://github.com/travisvn/chatterbox-tts-api))",
"Chatterbox Model": "Chatterbox 模型",
@@ -296,6 +300,7 @@
"tts_provider_tips.chatterbox": "自托管服务。运行兼容的 [Chatterbox TTS API](https://github.com/travisvn/chatterbox-tts-api),并填写以 `/v1` 结尾的 Base URL;API Key 通常可选。",
"tts_provider_tips.kokoro": "自托管、免费:运行兼容的 [Kokoro-FastAPI](https://github.com/remsky/Kokoro-FastAPI)(Apache-2.0 模型,CPU 即可),并填写以 `/v1` 结尾的 Base URL;音色列表自动从服务端读取。",
"tts_provider_tips.fish_audio": "需要 Fish Audio API Key,可在[开发者控制台](https://fish.audio/app/developers)获取;可在 [Fish Audio](https://fish.audio) 浏览更多音色或在 `config.toml` 中配置自定义音色;查看[价格与条款](https://fish.audio/pricing)。",
+ "tts_provider_tips.voxcpm": "需要 [ModelBest API Key](https://platform.modelbest.cn/console/keys) 和支持 `speech_synthesis` 能力的模型 ID。该 API 以流式 WAV 返回音频,本次接入使用默认音色。接口暂不支持数值语速,可在文案开头加入 `(语速稍快)` 等自然语言描述;参考音频复刻尚未包含。",
"Hide Log": "隐藏日志",
"Hide Basic Settings": "隐藏基础设置\n\n隐藏后,基础设置面板将不会显示在页面中。\n\n如需要再次显示,请在 `config.toml` 中设置 `hide_config = false`",
"LLM Settings": "**大模型设置**",