Grayscale/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(transcription): add shared voice input support (#4232)

Browse Source 
* feat(webui): add voice transcription input

* feat(webui): render ANSI output in code blocks

* refactor(webui): isolate voice recorder logic

* refactor(transcription): keep websocket ingress thin

* refactor(transcription): resolve channel audio settings on demand

* style(webui): neutralize voice waveform color

* feat(webui): add voice input tooltip

* feat(webui): add voice input keyboard shortcut

* fix(webui): distinguish voice shortcut platforms

* fix(webui): place voice button after model selector

* refactor(webui): share voice hold recording helpers

* fix(desktop): allow microphone voice input

* fix(webui): stabilize token usage month labels

* feat(webui): show voice input on settings overview

* fix(webui): label voice capability as recognition

* fix(webui): align capability overview status

* refactor(webui): isolate transcription socket handling

* fix(webui): soften silent voice waveform

* refactor(audio): clarify transcription service location

* docs(transcription): clarify audio and provider boundaries

* fix(exec): reduce session output polling flake
This commit is contained in:
Xubin Ren
2026-06-09 01:08:49 +08:00
committed by GitHub
parent 06d454a225
commit 9c81280300
49 changed files with 3071 additions and 257 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nanobot/config/schema.py
+15 -3
View File
@@ -39,8 +39,19 @@ class ChannelsConfig(Base):
show_reasoning: bool = True # surface model reasoning when channel implements it
extract_document_text: bool = True # extract text from document attachments before sending to the model
send_max_retries: int = Field(default=3, ge=0, le=10) # Max delivery attempts (initial send included)
transcription_provider: str = "groq" # Voice transcription backend: "groq" or "openai"
transcription_language: str | None = Field(default=None, pattern=r"^[a-z]{2,3}$") # Optional ISO-639-1 hint for audio transcription
transcription_provider: str = "groq" # Deprecated: use top-level transcription.provider
transcription_language: str | None = Field(default=None, pattern=r"^[a-z]{2,3}$") # Deprecated: use top-level transcription.language
class TranscriptionConfig(Base):
"""Cross-channel audio transcription configuration."""
enabled: bool = True
provider: Literal["groq", "openai"] | None = None
model: str | None = None
language: str | None = Field(default=None, pattern=r"^[a-z]{2,3}$")
max_duration_sec: int = Field(default=120, ge=1, le=600)
max_upload_mb: int = Field(default=25, ge=1, le=100)
class DreamConfig(Base):
@@ -167,7 +178,7 @@ class AgentsConfig(Base):
class ProviderConfig(Base):
"""LLM provider configuration."""
api_key: str | None = None
api_key: str | None = Field(default=None, repr=False)
api_base: str | None = None
api_type: Literal["auto", "chat_completions", "responses"] = "auto" # Request API surface
extra_headers: dict[str, str] | None = None # Custom headers (e.g. APP-Code for AiHubMix)
@@ -312,6 +323,7 @@ class Config(BaseSettings):
agents: AgentsConfig = Field(default_factory=AgentsConfig)
channels: ChannelsConfig = Field(default_factory=ChannelsConfig)
transcription: TranscriptionConfig = Field(default_factory=TranscriptionConfig)
providers: ProvidersConfig = Field(default_factory=ProvidersConfig)
api: ApiConfig = Field(default_factory=ApiConfig)
gateway: GatewayConfig = Field(default_factory=GatewayConfig)