supervoxtral 0.1.4__py3-none-any.whl → 0.3.0__py3-none-any.whl

{supervoxtral-0.1.4.dist-info → supervoxtral-0.3.0.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: supervoxtral
-Version: 0.1.4
-Summary: CLI/GUI audio recorder and transcription client using Mistral Voxtral (chat with audio and transcription).
+Version: 0.3.0
+Summary: CLI/GUI audio recorder with 2-step pipeline: transcription (Voxtral) then text transformation (LLM).
 License: MIT
 License-File: LICENSE
 Keywords: audio,cli,gui,mistral,transcription,voxtral,whisper
@@ -14,10 +14,7 @@ Requires-Dist: sounddevice
 Requires-Dist: soundfile
 Requires-Dist: typer
 Provides-Extra: dev
-Requires-Dist: black; extra == 'dev'
-Requires-Dist: mypy; extra == 'dev'
-Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: basedpyright; extra == 'dev'
 Requires-Dist: ruff; extra == 'dev'
-Requires-Dist: types-python-dotenv; extra == 'dev'
 Provides-Extra: gui
 Requires-Dist: pyside6-essentials; extra == 'gui'

supervoxtral-0.3.0.dist-info/RECORD

@@ -0,0 +1,18 @@
+svx/__init__.py,sha256=qPEe5u3PT8yOQN4MiOLj_Bd18HqcRb6fxnPDfdMUP7w,742
+svx/cli.py,sha256=7fzs85LT85RbZYtI8t-yOXKrRd9r-IzE1hnFJHNgxL4,9436
+svx/core/__init__.py,sha256=mhzXuIXo3kUzjWme0Bxhe4TQZQELlyEiG_89LUAPC7M,2856
+svx/core/audio.py,sha256=svyRWbPaUyYqbmGaLF8oUim-x5mj9zciv0XCqq2VGEU,7828
+svx/core/clipboard.py,sha256=IFtiN2SnYKQIu0WXx0hCK8syvDXanBpm1Jr2a8X7y9s,3692
+svx/core/config.py,sha256=Ib_lIKUFriW-B9i49zTUZE-YcOQYEkpBE3CF_WDzFlg,17060
+svx/core/pipeline.py,sha256=GhaOJtHGiwwsSv2EkNM-ZKu0DSm25xDeI9sNTLw7YJU,11612
+svx/core/prompt.py,sha256=OpS3XgusRwV4JP9cCzyk0DXcphcLcgHIPV89eoc2vFc,7282
+svx/core/storage.py,sha256=_w_rTOPoqlz0eoD2XHPNvHPQXgs6QxZ7SP4_IBT8Bx4,3223
+svx/providers/__init__.py,sha256=SzlSWpZSUIptbSrAnGfi0d0NX4hYTpT0ObWpYyskDdA,2634
+svx/providers/base.py,sha256=D_iDjhJuAGye-JjWbO-Rtl131kD6hgYQaspO53-6spo,3238
+svx/providers/mistral.py,sha256=ZkA02KDU-2ktdBM2tKUmTG8ZVnp8suE4g1TrPBpmqDA,6439
+svx/ui/qt_app.py,sha256=FDdxcgqzHi5HCsbmCzQtVEFTfcVaDLfiVgQe_8YHHoY,19993
+supervoxtral-0.3.0.dist-info/METADATA,sha256=vnKZuM96g1le-da4EVKOsECuSvIVpneE0xKq-DY-2_E,629
+supervoxtral-0.3.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+supervoxtral-0.3.0.dist-info/entry_points.txt,sha256=phJhRy3VkYHC6AR_tUB5CypHzG0ePRR9sB13HWE1vEg,36
+supervoxtral-0.3.0.dist-info/licenses/LICENSE,sha256=fCEBKmC4i-1WZAwoKjKWegfDd8qNsG8ECB7JyqoswyQ,1064
+supervoxtral-0.3.0.dist-info/RECORD,,

{supervoxtral-0.1.4.dist-info → supervoxtral-0.3.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.27.0
+Generator: hatchling 1.28.0
 Root-Is-Purelib: true
 Tag: py3-none-any

svx/cli.py

@@ -162,10 +162,14 @@ def record(
     ),
 ):
     """
-    Record audio from the microphone and send it to the selected provider.
+    Record audio from the microphone and process it via a 2-step pipeline.
+
+    Pipeline:
+    1. Transcription: audio -> text via dedicated transcription endpoint (always).
+    2. Transformation: text + prompt -> text via text-based LLM (when a prompt is provided).
 
     This CLI accepts only a small set of runtime flags. Most defaults (provider, format,
-    model, language, sample rate, channels, device,
+    model, chat_model, language, sample rate, channels, device,
     file retention, copy-to-clipboard)
     must be configured in the user's `config.toml` under [defaults].
 
@@ -178,11 +182,12 @@ def record(
     Flow:
     - Records WAV until you press Enter (CLI mode).
     - Optionally converts to MP3/Opus depending on config.
-    - Sends the file per provider rules.
+    - Transcribes via dedicated endpoint (step 1).
+    - If a prompt is provided, transforms the transcript via LLM (step 2).
     - Prints and saves the result.
 
     Note: In --transcribe mode, prompts (--user-prompt or --user-prompt-file) are ignored,
-    as it uses a dedicated transcription endpoint without prompting.
+    and only step 1 (transcription) is performed.
     """
     cfg = Config.load(log_level=log_level)
 

svx/core/audio.py

@@ -22,6 +22,7 @@ from pathlib import Path
 from threading import Event, Thread
 from typing import Any
 
+import numpy as np
 import sounddevice as sd
 import soundfile as sf
 
@@ -149,7 +150,12 @@ def record_wav(
     writer_stop = Event()
     start_time = time.time()
 
-    def audio_callback(indata, frames, time_info, status):
+    def audio_callback(
+        indata: np.ndarray[Any, np.dtype[np.int16]],
+        frames: int,
+        time_info: sd.CallbackFlags,
+        status: sd.CallbackFlags,
+    ) -> None:
         if status:
             logging.warning("SoundDevice status: %s", status)
         q.put(indata.copy())

svx/core/config.py

@@ -220,10 +220,17 @@ def init_user_config(force: bool = False, prompt_file: Path | None = None) -> Pa
         '# File format sent to the provider: "wav" | "mp3" | "opus"\n'
         '# Recording is always WAV; conversion is applied if "mp3" or "opus"\n'
         'format = "opus"\n\n'
-        "# Model to use on the provider side (example for Mistral Voxtral)\n"
+        "# Model for audio transcription (dedicated endpoint)\n"
         'model = "voxtral-mini-latest"\n\n'
+        "# Model for text transformation via LLM\n"
+        "# (applied after transcription when a prompt is used)\n"
+        'chat_model = "mistral-small-latest"\n\n'
         "# Language hint (may help the provider)\n"
         'language = "fr"\n\n'
+        "# Context bias: up to 100 words/phrases to help recognize specific vocabulary\n"
+        "# (proper nouns, technical terms, brand names, etc.)\n"
+        '# context_bias = ["SuperVoxtral", "Mistral AI", "Voxtral"]\n'
+        "context_bias = []\n\n"
         "# Audio recording parameters\n"
         "rate = 16000\n"
         "channels = 1\n"
@@ -271,7 +278,9 @@ class DefaultsConfig:
     provider: str = "mistral"
     format: str = "opus"
     model: str = "voxtral-mini-latest"
+    chat_model: str = "mistral-small-latest"
     language: str | None = None
+    context_bias: list[str] = field(default_factory=list)
     rate: int = 16000
     channels: int = 1
     device: str | None = None
@@ -315,7 +324,11 @@ class Config:
             "provider": str(user_defaults_raw.get("provider", "mistral")),
             "format": str(user_defaults_raw.get("format", "opus")),
             "model": str(user_defaults_raw.get("model", "voxtral-mini-latest")),
+            "chat_model": str(user_defaults_raw.get("chat_model", "mistral-small-latest")),
             "language": user_defaults_raw.get("language"),
+            "context_bias": list(user_defaults_raw.get("context_bias", []))
+            if isinstance(user_defaults_raw.get("context_bias"), list)
+            else [],
             "rate": int(user_defaults_raw.get("rate", 16000)),
             "channels": int(user_defaults_raw.get("channels", 1)),
             "device": user_defaults_raw.get("device"),
@@ -335,6 +348,9 @@ class Config:
         format_ = defaults_data["format"]
         if format_ not in {"wav", "mp3", "opus"}:
             raise ValueError("format must be one of wav|mp3|opus")
+        context_bias = defaults_data["context_bias"]
+        if len(context_bias) > 100:
+            raise ValueError("context_bias cannot contain more than 100 items (Mistral API limit)")
         defaults = DefaultsConfig(**defaults_data)
         # Conditional output directories
         if defaults.keep_audio_files:

svx/core/pipeline.py

@@ -12,18 +12,23 @@ import svx.core.config as config
 from svx.core.audio import convert_audio, record_wav, timestamp
 from svx.core.clipboard import copy_to_clipboard
 from svx.core.config import Config
-from svx.core.storage import save_transcript
+from svx.core.storage import save_text_file, save_transcript
 from svx.providers import get_provider
 
 
 class RecordingPipeline:
     """
-    Centralized pipeline for recording audio, transcribing via provider, saving outputs,
-    and copying to clipboard. Handles temporary files when not keeping audio.
+    Centralized pipeline for recording audio, transcribing via provider, optionally
+    transforming with a text LLM, saving outputs, and copying to clipboard.
 
+    Pipeline steps:
+    1. Transcription: audio -> text via dedicated transcription endpoint (always)
+    2. Transformation: text + prompt -> text via text-based LLM (when a prompt is provided)
+
+    Handles temporary files when not keeping audio.
     Supports runtime overrides like save_all for keeping all files and adding log handlers.
     Optional progress_callback for status updates (e.g., for GUI).
-    Supports transcribe_mode for pure transcription without prompt using dedicated endpoint.
+    Supports transcribe_mode for pure transcription without prompt (step 1 only).
     """
 
     def __init__(
@@ -136,31 +141,26 @@ class RecordingPipeline:
         self, wav_path: Path, duration: float, transcribe_mode: bool, user_prompt: str | None = None
     ) -> dict[str, Any]:
         """
-        Process recorded audio: convert if needed, transcribe, save, copy.
+        Process recorded audio: convert if needed, transcribe, optionally transform, save, copy.
+
+        Pipeline:
+        1. Transcription: audio -> text via dedicated endpoint (always)
+        2. Transformation: text + prompt -> text via LLM (when prompt is provided)
 
         Args:
             wav_path: Path to the recorded WAV file.
             duration: Recording duration in seconds.
-            transcribe_mode: Whether to use pure transcription mode.
-            user_prompt: User prompt to use (None for transcribe_mode).
+            transcribe_mode: Whether to use pure transcription mode (step 1 only).
+            user_prompt: User prompt to use for transformation (None for transcribe_mode).
 
         Returns:
-            Dict with 'text' (str), 'raw' (dict), 'duration' (float),
-            'paths' (dict of Path or None).
+            Dict with 'text' (str), 'raw_transcript' (str), 'raw' (dict),
+            'duration' (float), 'paths' (dict of Path or None).
         """
         # Resolve parameters
         provider = self.cfg.defaults.provider
         audio_format = self.cfg.defaults.format
         model = self.cfg.defaults.model
-        original_model = model
-        if transcribe_mode:
-            model = "voxtral-mini-latest"
-            if original_model != "voxtral-mini-latest":
-                logging.warning(
-                    "Transcribe mode: model override from '%s' to 'voxtral-mini-latest'\n"
-                    "(optimized for transcription).",
-                    original_model,
-                )
         language = self.cfg.defaults.language
         if wav_path.stem.endswith(".wav"):
             base = wav_path.stem.replace(".wav", "")
@@ -176,9 +176,11 @@ class RecordingPipeline:
                 final_user_prompt = self.cfg.resolve_prompt(self.user_prompt, self.user_prompt_file)
             else:
                 final_user_prompt = user_prompt
-            self._status("Transcribe mode not activated: using prompt.")
+            self._status("Prompt mode: transcription then transformation.")
         else:
-            self._status("Transcribe mode activated: no prompt used.")
+            self._status("Transcribe mode: transcription only, no prompt.")
+
+        logging.debug(f"Applied prompt: {final_user_prompt or 'None (transcribe mode)'}")
 
         paths: dict[str, Path | None] = {"wav": wav_path}
 
@@ -192,18 +194,22 @@ class RecordingPipeline:
             paths["converted"] = to_send_path
             _converted = True
 
-        # Transcribe
+        # Step 1: Transcription (always)
         self._status("Transcribing...")
         prov = get_provider(provider, cfg=self.cfg)
-        result = prov.transcribe(
-            to_send_path,
-            user_prompt=final_user_prompt,
-            model=model,
-            language=language,
-            transcribe_mode=transcribe_mode,
-        )
-        text = result["text"]
-        raw = result["raw"]
+        result = prov.transcribe(to_send_path, model=model, language=language)
+        raw_transcript = result["text"]
+
+        # Step 2: Transformation (if prompt)
+        if not transcribe_mode and final_user_prompt:
+            self._status("Applying prompt...")
+            chat_model = self.cfg.defaults.chat_model
+            chat_result = prov.chat(raw_transcript, final_user_prompt, model=chat_model)
+            text = chat_result["text"]
+            raw = {"transcription": result["raw"], "transformation": chat_result["raw"]}
+        else:
+            text = raw_transcript
+            raw = result["raw"]
 
         # Save if keeping transcripts
         if keep_transcript:
@@ -213,6 +219,12 @@ class RecordingPipeline:
             )
             paths["txt"] = txt_path
             paths["json"] = json_path
+
+            # Save raw transcript separately when transformation was applied
+            if not transcribe_mode and final_user_prompt:
+                raw_txt_path = self.cfg.transcripts_dir / f"{base}_{provider}_raw.txt"
+                save_text_file(raw_txt_path, raw_transcript)
+                paths["raw_txt"] = raw_txt_path
         else:
             paths["txt"] = None
             paths["json"] = None
@@ -228,6 +240,7 @@ class RecordingPipeline:
         logging.info("Processing finished (%.2fs)", duration)
         return {
             "text": text,
+            "raw_transcript": raw_transcript,
             "raw": raw,
             "duration": duration,
             "paths": paths,
@@ -261,8 +274,8 @@ class RecordingPipeline:
             stop_event: Optional event to signal recording stop (e.g., for GUI).
 
         Returns:
-            Dict with 'text' (str), 'raw' (dict), 'duration' (float),
-            'paths' (dict of Path or None).
+            Dict with 'text' (str), 'raw_transcript' (str), 'raw' (dict),
+            'duration' (float), 'paths' (dict of Path or None).
 
         Raises:
             Exception: On recording, conversion, or transcription errors.

svx/core/prompt.py

@@ -12,6 +12,7 @@ Intended to be small and dependency-light so it can be imported broadly.
 from __future__ import annotations
 
 import logging
+from collections.abc import Callable
 from pathlib import Path
 
 from .config import USER_PROMPT_DIR, Config, PromptEntry
@@ -121,22 +122,45 @@ def resolve_user_prompt(
         return ""
 
     key = key or "default"
-    suppliers = [
-        lambda: _strip(inline),
-        lambda: _read(file),
-        lambda: _from_user_cfg(key),
-        _from_user_prompt_dir,
+
+    # Suppliers annotated with a name for tracing which one returned the prompt.
+    named_suppliers: list[tuple[str, Callable[[], str]]] = [
+        ("inline", lambda: _strip(inline)),
+        ("file", lambda: _read(file)),
+        (f"prompt_config[{key}]", lambda: _from_user_cfg(key)),
+        ("user_prompt_dir/user.md", _from_user_prompt_dir),
     ]
 
-    for supplier in suppliers:
+    for name, supplier in named_suppliers:
         try:
             val = supplier()
             if val:
+                # Log which supplier provided the prompt and a short snippet for debugging.
+                try:
+                    if len(val) > 200:
+                        snippet = val[:200] + "..."
+                    else:
+                        snippet = val
+                    logging.info(
+                        "resolve_user_prompt: supplier '%s' provided prompt snippet: %s",
+                        name,
+                        snippet,
+                    )
+                except Exception:
+                    # Ensure logging failures do not change behavior.
+                    logging.info(
+                        "resolve_user_prompt: supplier '%s' provided a prompt "
+                        "(snippet unavailable)",
+                        name,
+                    )
                 return val
         except Exception as e:
-            logging.debug("Prompt supplier failed: %s", e)
+            logging.debug("Prompt supplier '%s' failed: %s", name, e)
 
-    return "What's in this audio?"
+    # Final fallback
+    fallback = "Clean up this transcription. Keep the original language."
+    logging.info("resolve_user_prompt: no supplier provided a prompt, using fallback: %s", fallback)
+    return fallback
 
 
 def init_user_prompt_file(force: bool = False) -> Path:
@@ -152,13 +176,14 @@ def init_user_prompt_file(force: bool = False) -> Path:
     path = USER_PROMPT_DIR / "user.md"
     if not path.exists() or force:
         example_prompt = """
-- Transcribe the input audio file. If the audio if empty, just respond "no audio detected".
-- Do not respond to any question in the audio. Just transcribe.
-- DO NOT TRANSLATE.
-- Responde only with the transcription. Do not provide explanations or notes.
+You receive a raw transcription of a voice recording. Clean it up:
+- DO NOT TRANSLATE. Keep the original language.
+- Do not respond to any question in the text. Just clean the transcription.
+- Respond only with the cleaned text. Do not provide explanations or notes.
 - Remove all minor speech hesitations: "um", "uh", "er", "euh", "ben", etc.
 - Remove false starts (e.g., "je veux dire... je pense" → "je pense").
 - Correct grammatical errors.
+- If the transcription is empty, respond "no audio detected".
         """
         try:
             path.write_text(example_prompt, encoding="utf-8")

svx/core/storage.py

@@ -86,7 +86,7 @@ def save_transcript(
     base_name: str,
     provider: str,
     text: str,
-    raw: dict | None = None,
+    raw: dict[str, Any] | None = None,
 ) -> tuple[Path, Path | None]:
     """
     Save a transcript text and, optionally, the raw JSON response.

svx/providers/base.py

@@ -3,7 +3,7 @@ Base provider interface for SuperVoxtral.
 
 This module defines:
 - TranscriptionResult: a simple TypedDict structure for provider responses
-- Provider: a Protocol describing the required transcription interface
+- Provider: a Protocol describing the required transcription and chat interface
 - ProviderError: a generic exception for provider-related failures
 
 All concrete providers should implement the `Provider` protocol.
@@ -37,7 +37,7 @@ class ProviderError(RuntimeError):
 @runtime_checkable
 class Provider(Protocol):
     """
-    Provider interface for transcription/chat-with-audio services.
+    Provider interface for transcription and text transformation services.
 
     Implementations should be side-effect free aside from network I/O and must
     raise `ProviderError` (or a subclass) for expected provider failures
@@ -47,7 +47,8 @@ class Provider(Protocol):
         name: A short, lowercase, unique identifier for the provider (e.g. "mistral").
 
     Required methods:
-        transcribe: Perform the transcription given an audio file and optional user prompt.
+        transcribe: Perform audio transcription via a dedicated endpoint.
+        chat: Transform text with a prompt via a text-based LLM.
     """
 
     # Short, unique name (e.g., "mistral", "whisper")
@@ -56,21 +57,16 @@ class Provider(Protocol):
     def transcribe(
         self,
         audio_path: Path,
-        user_prompt: str | None,
         model: str | None = None,
         language: str | None = None,
-        transcribe_mode: bool = False,
     ) -> TranscriptionResult:
         """
-        Transcribe or process `audio_path` and return a normalized result.
+        Transcribe `audio_path` using a dedicated transcription endpoint.
 
         Args:
             audio_path: Path to an audio file (wav/mp3/opus...) to send to the provider.
-            user_prompt: Optional user prompt to guide the transcription or analysis.
             model: Optional provider-specific model identifier.
             language: Optional language hint/constraint (e.g., "en", "fr").
-            transcribe_mode: Optional bool to enable specialized modes like pure
-                             transcription (default False).
 
         Returns:
             TranscriptionResult including a human-readable `text` and
@@ -81,3 +77,27 @@ class Provider(Protocol):
             Exception: For unexpected failures (network issues, serialization, etc.).
         """
         ...
+
+    def chat(
+        self,
+        text: str,
+        prompt: str,
+        model: str | None = None,
+    ) -> TranscriptionResult:
+        """
+        Transform `text` using a text-based LLM with the given `prompt`.
+
+        Args:
+            text: Input text (e.g., raw transcription) to process.
+            prompt: System prompt guiding the transformation.
+            model: Optional provider-specific model identifier for the chat LLM.
+
+        Returns:
+            TranscriptionResult including the transformed `text` and
+            provider `raw` payload.
+
+        Raises:
+            ProviderError: For known/handled provider errors (e.g., missing API key).
+            Exception: For unexpected failures (network issues, serialization, etc.).
+        """
+        ...

svx/providers/mistral.py

@@ -1,22 +1,18 @@
 """
 Mistral provider implementation for SuperVoxtral.
 
-This module provides a concrete Provider that uses Mistral's
-"chat with audio" capability (Voxtral) to process audio and return text.
+This module provides a concrete Provider that uses Mistral's dedicated
+transcription endpoint (Voxtral) and text-based LLM chat for transformation.
 
 Requirements:
 - User config must define [providers.mistral].api_key in config.toml.
 - Package 'mistralai' installed and importable.
 
-The provider composes messages with:
-- User content including the audio (base64) and optional user prompt text.
-
 It returns a normalized TranscriptionResult: {"text": str, "raw": dict}.
 """
 
 from __future__ import annotations
 
-import base64
 import json
 import logging
 from pathlib import Path
@@ -29,14 +25,6 @@ from .base import Provider, ProviderError, TranscriptionResult
 __all__ = ["MistralProvider"]
 
 
-def _read_file_as_base64(path: Path) -> str:
-    """
-    Read a file and return its base64-encoded string.
-    """
-    data = Path(path).read_bytes()
-    return base64.b64encode(data).decode("utf-8")
-
-
 def _extract_text_from_response(resp: Any) -> str:
     """
     Attempt to robustly extract the textual content from a Mistral response.
@@ -89,9 +77,10 @@ def _normalize_raw_response(resp: Any) -> dict[str, Any]:
 
 class MistralProvider(Provider):
     """
-    Mistral Voxtral provider implementation.
+    Mistral provider implementation.
 
-    Uses the Mistral Python SDK to call `chat.with_audio` endpoint.
+    Uses the dedicated transcription endpoint for audio-to-text
+    and the chat endpoint for text transformation via LLM.
     """
 
     name = "mistral"
@@ -103,27 +92,21 @@ class MistralProvider(Provider):
         self.api_key = mistral_cfg.api_key
         if not self.api_key:
             raise ProviderError("Missing providers.mistral.api_key in user config (config.toml).")
+        self.context_bias = cfg.defaults.context_bias
 
     def transcribe(
         self,
         audio_path: Path,
-        user_prompt: str | None,
-        model: str | None = "voxtral-small-latest",
+        model: str | None = "voxtral-mini-latest",
         language: str | None = None,
-        transcribe_mode: bool = False,
     ) -> TranscriptionResult:
         """
-        Transcribe/process audio using Mistral's chat-with-audio or transcription endpoint.
+        Transcribe audio using Mistral's dedicated transcription endpoint.
 
         Args:
             audio_path: Path to wav/mp3/opus file to send.
-            user_prompt: Optional user prompt to include with the audio
-                         (ignored in transcribe_mode).
-            model: Voxtral model identifier (default: "voxtral-small-latest" for chat,
-                   "voxtral-mini-latest" for transcribe).
-            language: Optional language hint for transcription (used only in
-                      transcribe_mode).
-            transcribe_mode: If True, use dedicated transcription endpoint without prompt.
+            model: Voxtral model identifier (default: "voxtral-mini-latest").
+            language: Optional language hint for transcription.
 
         Returns:
             TranscriptionResult: {"text": text, "raw": raw_dict}
@@ -143,47 +126,71 @@ class MistralProvider(Provider):
 
         client = Mistral(api_key=self.api_key)
 
-        if transcribe_mode:
-            if user_prompt:
-                logging.warning("Transcribe mode: user_prompt is ignored.")
-            model_name = model or "voxtral-mini-latest"
-            logging.info(
-                "Calling Mistral transcription endpoint model=%s with audio=%s (%s), language=%s",
-                model_name,
-                Path(audio_path).name,
-                Path(audio_path).suffix,
-                language or "auto",
+        model_name = model or "voxtral-mini-latest"
+        logging.info(
+            "Calling Mistral transcription endpoint model=%s with audio=%s (%s),"
+            " language=%s, context_bias=%d items",
+            model_name,
+            Path(audio_path).name,
+            Path(audio_path).suffix,
+            language or "auto",
+            len(self.context_bias),
+        )
+        with open(audio_path, "rb") as f:
+            resp = client.audio.transcriptions.complete(
+                model=model_name,
+                file={"content": f, "file_name": Path(audio_path).name},
+                language=language,
+                context_bias=self.context_bias if self.context_bias else None,
             )
-            with open(audio_path, "rb") as f:
-                resp = client.audio.transcriptions.complete(
-                    model=model_name,
-                    file={"content": f, "file_name": Path(audio_path).name},
-                    language=language,
-                )
-            text = resp.text
-            raw = _normalize_raw_response(resp)
-        else:
-            audio_b64 = _read_file_as_base64(Path(audio_path))
-
-            # Compose messages (user only)
-            messages: list[dict[str, Any]] = []
-            user_content: list[dict[str, Any]] = [{"type": "input_audio", "input_audio": audio_b64}]
-            if user_prompt:
-                user_content.append({"type": "text", "text": user_prompt})
-            messages.append({"role": "user", "content": user_content})
-
-            # Execute request
-            model_name = model or "voxtral-small-latest"
-            logging.info(
-                "Calling Mistral chat-with-audio model=%s with audio=%s (%s)",
-                model_name,
-                Path(audio_path).name,
-                Path(audio_path).suffix,
-            )
-            resp = client.chat.complete(model=model_name, messages=cast(Any, messages))
-
-            # Extract normalized text and raw payload
-            text = _extract_text_from_response(resp)
-            raw = _normalize_raw_response(resp)
+        text = resp.text
+        raw = _normalize_raw_response(resp)
 
         return TranscriptionResult(text=text, raw=raw)
+
+    def chat(
+        self,
+        text: str,
+        prompt: str,
+        model: str | None = None,
+    ) -> TranscriptionResult:
+        """
+        Transform text using Mistral's chat endpoint with a system prompt.
+
+        Args:
+            text: Input text (e.g., raw transcription) to process.
+            prompt: System prompt guiding the transformation.
+            model: Model identifier (default: None, caller should provide).
+
+        Returns:
+            TranscriptionResult: {"text": text, "raw": raw_dict}
+
+        Raises:
+            ProviderError: for expected configuration/import errors.
+        """
+        try:
+            from mistralai import Mistral
+        except Exception as e:
+            raise ProviderError(
+                "Failed to import 'mistralai'. Ensure the 'mistralai' package is installed."
+            ) from e
+
+        client = Mistral(api_key=self.api_key)
+
+        model_name = model or "mistral-small-latest"
+        logging.info(
+            "Calling Mistral chat endpoint model=%s for text transformation",
+            model_name,
+        )
+
+        messages: list[dict[str, Any]] = [
+            {"role": "system", "content": prompt},
+            {"role": "user", "content": text},
+        ]
+
+        resp = client.chat.complete(model=model_name, messages=cast(Any, messages))
+
+        result_text = _extract_text_from_response(resp)
+        raw = _normalize_raw_response(resp)
+
+        return TranscriptionResult(text=result_text, raw=raw)

svx/ui/qt_app.py

@@ -119,7 +119,7 @@ class WaveformWidget(QWidget):
     waveform to indicate recording activity. It is lightweight and self-contained.
     """
 
-    def __init__(self, parent=None, height: int = 64) -> None:
+    def __init__(self, parent: QWidget | None = None, height: int = 64) -> None:
         super().__init__(parent)
         self.setMinimumHeight(height)
         self.setMaximumHeight(height)
@@ -273,10 +273,39 @@ class RecorderWorker(QObject):
                 self.canceled.emit()
                 return
             self.status.emit("Processing in progress...")
+            # Wait for user to select mode in the GUI
             while self.mode is None:
                 time.sleep(0.05)
+
+            # Log the selected mode/key for debugging prompt application
+            try:
+                logging.info("RecorderWorker: selected mode/key: %s", self.mode)
+            except Exception:
+                # ensure failures in logging don't break the worker
+                pass
+
             transcribe_mode = self.mode == "transcribe"
-            user_prompt = None if transcribe_mode else self._resolve_user_prompt(self.mode)
+            if transcribe_mode:
+                user_prompt = None
+            else:
+                # Resolve the user prompt for the selected key and log a short snippet
+                user_prompt = self._resolve_user_prompt(self.mode)
+                try:
+                    if user_prompt:
+                        snippet = (
+                            user_prompt[:200] + "..." if len(user_prompt) > 200 else user_prompt
+                        )
+                    else:
+                        snippet = "<EMPTY>"
+                    logging.info(
+                        "RecorderWorker: resolved prompt snippet for key '%s': %s",
+                        self.mode,
+                        snippet,
+                    )
+                except Exception:
+                    # avoid breaking the flow on logging errors
+                    pass
+
             result = pipeline.process(wav_path, duration, transcribe_mode, user_prompt)
             keep_audio = self.save_all or self.cfg.defaults.keep_audio_files
             pipeline.clean(wav_path, result["paths"], keep_audio)
@@ -383,13 +412,15 @@ class RecorderWindow(QWidget):
         button_layout.addStretch()
         self._transcribe_btn = QPushButton("Transcribe")
         self._transcribe_btn.setToolTip("Stop and transcribe without prompt")
-        self._transcribe_btn.clicked.connect(lambda: self._on_mode_selected("transcribe"))
+        self._transcribe_btn.clicked.connect(
+            lambda checked=False, m="transcribe": self._on_mode_selected(m)
+        )
         button_layout.addWidget(self._transcribe_btn)
         self._prompt_buttons: dict[str, QPushButton] = {}
         for key in self.prompt_keys:
             btn = QPushButton(key.capitalize())
             btn.setToolTip(f"Stop and transcribe with '{key}' prompt")
-            btn.clicked.connect(lambda k=key: self._on_mode_selected(k))
+            btn.clicked.connect(lambda checked=False, k=key: self._on_mode_selected(k))
             self._prompt_buttons[key] = btn
             button_layout.addWidget(btn)
         self._cancel_btn = QPushButton("Cancel")

supervoxtral-0.1.4.dist-info/RECORD

@@ -1,18 +0,0 @@
-svx/__init__.py,sha256=qPEe5u3PT8yOQN4MiOLj_Bd18HqcRb6fxnPDfdMUP7w,742
-svx/cli.py,sha256=3AirsBynuq2rcz-4C8hbZ69JztkgA7LTMGmL6ym7nyY,9167
-svx/core/__init__.py,sha256=mhzXuIXo3kUzjWme0Bxhe4TQZQELlyEiG_89LUAPC7M,2856
-svx/core/audio.py,sha256=r0m5T1uzdsJ1j9YXgQ5clv15dvMwZBp_bk2aLpjnrkc,7684
-svx/core/clipboard.py,sha256=IFtiN2SnYKQIu0WXx0hCK8syvDXanBpm1Jr2a8X7y9s,3692
-svx/core/config.py,sha256=e2tTGjjPcUYFctB28Ha90G-W44mF_0eWey1zpSyZkBo,16095
-svx/core/pipeline.py,sha256=nqvCgK5Pbyx18mfACrN_mIDt546Bh7fKA6MF4XG1hxM,10637
-svx/core/prompt.py,sha256=yO8UbpFg7n1IT7wFjSQ7NUTbrqxuwPhdnxkTH4Iu7XU,5967
-svx/core/storage.py,sha256=5_xKYEpvDhaixRxmSTBlyX_jt8ssjHwHzX9VodcrtJw,3213
-svx/providers/__init__.py,sha256=SzlSWpZSUIptbSrAnGfi0d0NX4hYTpT0ObWpYyskDdA,2634
-svx/providers/base.py,sha256=YoiI8KWVRGISh7dx9XXPr1Q1a7ZDu8vfeJFlPbcKr20,2695
-svx/providers/mistral.py,sha256=vrBatNZg0zGNkJ5Qfnfz6ZwP6QtBgIt9sT_w59zkSO0,6636
-svx/ui/qt_app.py,sha256=6LOMeMjkMmYylu6H_prDRmPDsL0s4PVMZqfbflByCMs,18808
-supervoxtral-0.1.4.dist-info/METADATA,sha256=0w_i5geOKu8F9x7eviNboDNt-PTy6FS3WHe3cCx4eHg,753
-supervoxtral-0.1.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-supervoxtral-0.1.4.dist-info/entry_points.txt,sha256=phJhRy3VkYHC6AR_tUB5CypHzG0ePRR9sB13HWE1vEg,36
-supervoxtral-0.1.4.dist-info/licenses/LICENSE,sha256=fCEBKmC4i-1WZAwoKjKWegfDd8qNsG8ECB7JyqoswyQ,1064
-supervoxtral-0.1.4.dist-info/RECORD,,