wx44wx/AI-VideoAssistant
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add Volcengine support for TTS and ASR services

Browse Source 
- Introduced Volcengine as a new provider for both TTS and ASR services.
- Updated configuration files to include Volcengine-specific parameters such as app_id, resource_id, and uid.
- Enhanced the ASR service to support streaming mode with Volcengine's API.
- Modified existing tests to validate the integration of Volcengine services.
- Updated documentation to reflect the addition of Volcengine as a supported provider for TTS and ASR.
- Refactored service factory to accommodate Volcengine alongside existing providers.
This commit is contained in:
Xin Wang
2026-03-08 23:09:50 +08:00
parent 3604db21eb
commit aeeeee20d1
18 changed files with 1256 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
engine/app/config.py
View File

@@ -71,11 +71,15 @@ class Settings(BaseSettings):
# TTS Configuration
tts_provider: str = Field(
default="openai_compatible",
description="TTS provider (openai_compatible, siliconflow, dashscope)"
description="TTS provider (openai_compatible, siliconflow, dashscope, volcengine)"
)
tts_api_url: Optional[str] = Field(default=None, description="TTS provider API URL")
tts_model: Optional[str] = Field(default=None, description="TTS model name")
tts_voice: str = Field(default="anna", description="TTS voice name")
tts_app_id: Optional[str] = Field(default=None, description="Provider-specific TTS app ID")
tts_resource_id: Optional[str] = Field(default=None, description="Provider-specific TTS resource ID")
tts_cluster: Optional[str] = Field(default=None, description="Provider-specific TTS cluster")
tts_uid: Optional[str] = Field(default=None, description="Provider-specific TTS user ID")
tts_mode: str = Field(
default="commit",
description="DashScope-only TTS mode (commit, server_commit). Ignored for non-dashscope providers."
@@ -85,10 +89,18 @@ class Settings(BaseSettings):
# ASR Configuration
asr_provider: str = Field(
default="openai_compatible",
description="ASR provider (openai_compatible, buffered, siliconflow, dashscope)"
description="ASR provider (openai_compatible, buffered, siliconflow, dashscope, volcengine)"
)
asr_api_url: Optional[str] = Field(default=None, description="ASR provider API URL")
asr_model: Optional[str] = Field(default=None, description="ASR model name")
asr_app_id: Optional[str] = Field(default=None, description="Provider-specific ASR app ID")
asr_resource_id: Optional[str] = Field(default=None, description="Provider-specific ASR resource ID")
asr_cluster: Optional[str] = Field(default=None, description="Provider-specific ASR cluster")
asr_uid: Optional[str] = Field(default=None, description="Provider-specific ASR user ID")
asr_request_params_json: Optional[str] = Field(
default=None,
description="Provider-specific ASR request params as JSON string"
)
asr_enable_interim: bool = Field(default=False, description="Enable interim transcripts for offline ASR")
asr_interim_interval_ms: int = Field(default=500, description="Interval for interim ASR results in ms")
asr_min_audio_ms: int = Field(default=300, description="Minimum audio duration before first ASR result")