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

* 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

nanobot/channels/base.py

@@ -28,10 +28,6 @@ class BaseChannel(ABC):
 
     name: str = "base"
     display_name: str = "Base"
-    transcription_provider: str = "groq"
-    transcription_api_key: str = ""
-    transcription_api_base: str = ""
-    transcription_language: str | None = None
     send_progress: bool = True
     send_tool_hints: bool = False
     show_reasoning: bool = True
@@ -51,24 +47,14 @@ class BaseChannel(ABC):
 
     async def transcribe_audio(self, file_path: str | Path) -> str:
         """Transcribe an audio file via Whisper (OpenAI or Groq). Returns empty string on failure."""
-        if not self.transcription_api_key:
-            return ""
         try:
-            if self.transcription_provider == "openai":
-                from nanobot.providers.transcription import OpenAITranscriptionProvider
-                provider = OpenAITranscriptionProvider(
-                    api_key=self.transcription_api_key,
-                    api_base=self.transcription_api_base or None,
-                    language=self.transcription_language or None,
-                )
-            else:
-                from nanobot.providers.transcription import GroqTranscriptionProvider
-                provider = GroqTranscriptionProvider(
-                    api_key=self.transcription_api_key,
-                    api_base=self.transcription_api_base or None,
-                    language=self.transcription_language or None,
-                )
-            return await provider.transcribe(file_path)
+            from nanobot.audio.transcription import (
+                resolve_transcription_config,
+                transcribe_audio_file,
+            )
+            from nanobot.config.loader import load_config
+
+            return await transcribe_audio_file(file_path, resolve_transcription_config(load_config()))
         except Exception:
             self.logger.exception("Audio transcription failed")
             return ""

nanobot/channels/manager.py

@@ -80,11 +80,6 @@ class ChannelManager:
         """Initialize channels discovered via pkgutil scan + entry_points plugins."""
         from nanobot.channels.registry import discover_channel_names, discover_enabled
 
-        transcription_provider = self.config.channels.transcription_provider
-        transcription_key = self._resolve_transcription_key(transcription_provider)
-        transcription_base = self._resolve_transcription_base(transcription_provider)
-        transcription_language = self.config.channels.transcription_language
-
         # Collect enabled module names first, then only import those.
         # Channel configs live in ChannelsConfig's extra fields (via
         # extra="allow"), so we enumerate candidates from pkgutil scan
@@ -135,10 +130,6 @@ class ChannelManager:
                     )
                     kwargs["gateway"] = gateway
                 channel = cls(section, self.bus, **kwargs)
-                channel.transcription_provider = transcription_provider
-                channel.transcription_api_key = transcription_key
-                channel.transcription_api_base = transcription_base
-                channel.transcription_language = transcription_language
                 channel.send_progress = self._resolve_bool_override(
                     section, "send_progress", self.config.channels.send_progress,
                 )
@@ -155,24 +146,6 @@ class ChannelManager:
 
         self._validate_allow_from()
 
-    def _resolve_transcription_key(self, provider: str) -> str:
-        """Pick the API key for the configured transcription provider."""
-        try:
-            if provider == "openai":
-                return self.config.providers.openai.api_key
-            return self.config.providers.groq.api_key
-        except AttributeError:
-            return ""
-
-    def _resolve_transcription_base(self, provider: str) -> str:
-        """Pick the API base URL for the configured transcription provider."""
-        try:
-            if provider == "openai":
-                return self.config.providers.openai.api_base or ""
-            return self.config.providers.groq.api_base or ""
-        except AttributeError:
-            return ""
-
     def _validate_allow_from(self) -> None:
         for name, ch in self.channels.items():
             cfg = ch.config

nanobot/channels/websocket.py

@@ -45,6 +45,7 @@ from nanobot.webui.http_utils import (
     query_first as _query_first,
 )
 from nanobot.webui.mcp_presets_api import normalize_mcp_preset_mentions
+from nanobot.webui.transcription_ws import webui_transcription_event
 from nanobot.webui.websocket_logging import websockets_server_logger
 
 
@@ -235,7 +236,7 @@ _VIDEO_MIME_ALLOWED: frozenset[str] = frozenset({
 
 _UPLOAD_MIME_ALLOWED: frozenset[str] = _IMAGE_MIME_ALLOWED | _VIDEO_MIME_ALLOWED
 
-_DATA_URL_MIME_RE = re.compile(r"^data:([^;]+);base64,", re.DOTALL)
+_DATA_URL_MIME_RE = re.compile(r"^data:([^;,]+)(?:;[^,]*)*;base64,", re.DOTALL)
 
 
 def _extract_data_url_mime(url: str) -> str | None:
@@ -419,7 +420,6 @@ class WebSocketChannel(BaseChannel):
         return None
 
     # -- Server lifecycle and connection ingress ---------------------------
-    # -- Server lifecycle and connection ingress ---------------------------
 
     async def start(self) -> None:
         from nanobot.utils.logging_bridge import redirect_lib_logging
@@ -703,6 +703,10 @@ class WebSocketChannel(BaseChannel):
                 workspace_scope=scope.payload(),
             )
             return
+        if t == "transcribe_audio":
+            event, payload = await webui_transcription_event(envelope)
+            await self._send_event(connection, event, **payload)
+            return
         if t == "message":
             cid = envelope.get("chat_id")
             content = envelope.get("content")