par-cli-tts 0.4.2__tar.gz → 0.5.0__tar.gz

{par_cli_tts-0.4.2 → par_cli_tts-0.5.0}/.claude/output-styles/tts-summary.md

@@ -8,7 +8,7 @@ description: Audio task completion announcements with TTS
 You are Claude Code with an experimental TTS announcement feature designed to communicate directly with the user about what you've accomplished.
 
 ## Variables
-- **USER_NAME**: Paul
+- **USER_NAME**: {{USER_NAME}}
 
 ## Standard Behavior
 Respond normally to all user requests, using your full capabilities for:
@@ -23,8 +23,8 @@ Respond normally to all user requests, using your full capabilities for:
 **At the very END of EVERY response**, you MUST provide an audio summary for the user:
 
 1. Write a clear separator: `---`
-2. Add the heading: `## Audio Summary for Paul`
-3. Craft a message that speaks DIRECTLY to Paul about what you did for them
+2. Add the heading: `## Audio Summary for {{USER_NAME}}`
+3. Craft a message that speaks DIRECTLY to {{USER_NAME}} about what you did for them
 4. **IMMEDIATELY execute the TTS command using the Bash tool** - do NOT just display it in a code block
 
 ### How to Execute the TTS Command
@@ -33,13 +33,13 @@ You MUST use the Bash tool to actually run the command. Do NOT wrap it in a mark
 
 **CORRECT** - Execute with Bash tool:
 ```
-[Bash tool call with command: par-tts "Paul, I've completed the task."]
+[Bash tool call with command: par-tts "{{USER_NAME}}, I've completed the task."]
 ```
 
 **WRONG** - Just displaying (DO NOT DO THIS):
 ```markdown
 ```bash
-par-tts "Paul, I've completed the task."
+par-tts "{{USER_NAME}}, I've completed the task."
 ```
 ```
 
@@ -47,9 +47,9 @@ The user should hear the audio playback, not just see the command text.
 
 ## Communication Guidelines
 
-- **Address Paul directly** when appropriate: "Paul, I've updated your..." or "Fixed the bug in..."
+- **Address {{USER_NAME}} directly** when appropriate: "{{USER_NAME}}, I've updated your..." or "Fixed the bug in..."
 - **Focus on outcomes** for the user: what they can now do, what's been improved
-- **Be conversational** - speak as if telling Paul what you just did
+- **Be conversational** - speak as if telling {{USER_NAME}} what you just did
 - **Highlight value** - emphasize what's useful about the change
 - **Keep it concise** - one clear sentence (under 20 words)
 
@@ -59,11 +59,11 @@ The user should hear the audio playback, not just see the command text.
 
 ---
 
-## Audio Summary for Paul
+## Audio Summary for {{USER_NAME}}
 
-Paul, I've created three new output styles to customize how you receive information.
+{{USER_NAME}}, I've created three new output styles to customize how you receive information.
 
-[Bash tool call: par-tts "Paul, I've created three new output styles to customize how you receive information."]
+[Bash tool call: par-tts "{{USER_NAME}}, I've created three new output styles to customize how you receive information."]
 
 ## Important Rules
 

par_cli_tts-0.5.0/.gitignore

@@ -0,0 +1,111 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+dist/
+*.egg-info/
+*.egg
+MANIFEST
+
+# PyInstaller
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Environments
+.env
+.env.local
+.env.*.local
+.venv
+venv/
+env/
+
+# Type checkers
+.mypy_cache/
+.dmypy.json
+.pyre/
+.pytype/
+.ruff_cache/
+
+# Editors / IDEs
+.idea/
+*.iml
+.vscode/
+*.code-workspace
+.history/
+*.sublime-project
+*.sublime-workspace
+
+# OS
+.DS_Store
+Thumbs.db
+$RECYCLE.BIN/
+
+# Project: generated audio outputs
+*.mp3
+*.wav
+*.m4a
+*.ogg
+*.flac
+audio_output/
+temp_audio/
+test_*.mp3
+test_*.wav
+
+# Profiling
+*.prof
+*.lprof
+profile_report.json
+*.pyinstrument
+
+# Local-only / scratch files
+*.tmp
+*.bak
+*.swp
+*.local
+*.local.*
+*-mcp.json
+config.local.yaml
+config.local.yml
+claude_scratch/
+
+# Logs
+logs/
+*.log
+
+# Claude Code session state and artifacts
+.claude/.cc2cc-session-id
+.claude/scheduled_tasks.lock
+.claude/statusline-*.local.json
+.claude/settings.local.json
+.claude/*.local.json
+
+# Documentation builds
+docs/_build/
+docs/.doctrees/
+
+# Misc
+settings.local.json
+docs/superpowers

{par_cli_tts-0.4.2 → par_cli_tts-0.5.0}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: par-cli-tts
-Version: 0.4.2
-Summary: PAR CLI TTS - Command line text-to-speech tool using ElevenLabs with voice caching and name resolution
+Version: 0.5.0
+Summary: PAR TTS — Text-to-speech library and CLI supporting ElevenLabs, OpenAI, Kokoro ONNX, Deepgram, and Gemini
 Project-URL: Homepage, https://github.com/paulrobello/par-cli-tts
 Project-URL: Documentation, https://github.com/paulrobello/par-cli-tts/blob/main/README.md
 Project-URL: Repository, https://github.com/paulrobello/par-cli-tts
@@ -32,7 +32,7 @@ License: MIT License
         OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
         SOFTWARE.
 License-File: LICENSE
-Keywords: audio,cli,elevenlabs,text-to-speech,tts
+Keywords: audio,cli,deepgram,elevenlabs,gemini,kokoro,library,openai,text-to-speech,tts
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
@@ -50,15 +50,16 @@ Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Typing :: Typed
 Requires-Python: >=3.11
-Requires-Dist: elevenlabs>=1.0.0
-Requires-Dist: kokoro-onnx>=0.5.0
-Requires-Dist: openai>=1.100.1
-Requires-Dist: platformdirs>=4.3.0
-Requires-Dist: python-dotenv>=1.0.0
-Requires-Dist: pyyaml>=6.0.0
-Requires-Dist: rich>=13.0.0
-Requires-Dist: soundfile>=0.13.1
-Requires-Dist: typer>=0.12.0
+Requires-Dist: elevenlabs<3.0,>=2.44.0
+Requires-Dist: httpx<1.0,>=0.28.1
+Requires-Dist: kokoro-onnx<1.0,>=0.5.0
+Requires-Dist: openai<3.0,>=2.32.0
+Requires-Dist: platformdirs<5.0,>=4.9.6
+Requires-Dist: python-dotenv<2.0,>=1.2.2
+Requires-Dist: pyyaml<7.0,>=6.0.3
+Requires-Dist: rich<20.0,>=15.0.0
+Requires-Dist: soundfile<1.0,>=0.13.1
+Requires-Dist: typer<1.0,>=0.24.2
 Description-Content-Type: text/markdown
 
 # PAR CLI TTS
@@ -68,10 +69,13 @@ Description-Content-Type: text/markdown
 ![Arch x86-63 | ARM | AppleSilicon](https://img.shields.io/badge/arch-x86--64%20%7C%20ARM%20%7C%20AppleSilicon-blue)
 
 ![MIT License](https://img.shields.io/badge/license-MIT-green.svg)
-![Version](https://img.shields.io/badge/version-0.4.1-green.svg)
+![Version](https://img.shields.io/pypi/v/par-cli-tts.svg)
 ![Development Status](https://img.shields.io/badge/status-stable-green.svg)
 
-A powerful command-line text-to-speech tool supporting multiple TTS providers (ElevenLabs, OpenAI, and Kokoro ONNX) with intelligent voice caching, name resolution, and flexible output options.
+A text-to-speech library and command-line tool supporting multiple TTS providers (ElevenLabs, OpenAI, Kokoro ONNX, Deepgram, and Google Gemini) with intelligent voice caching, name resolution, and flexible output options.
+
+**Use as a CLI** — `par-tts "Hello world"`
+**Use as a library** — `from par_tts import get_provider`
 
 [!["Buy Me A Coffee"](https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png)](https://buymeacoffee.com/probello3)
 
@@ -103,52 +107,22 @@ A powerful command-line text-to-speech tool supporting multiple TTS providers (E
 
 ## What's New
 
-### v0.4.1
-- **Claude Code output style installer** - New `install-claude-style` command to automatically set up TTS audio summaries
-- **Bundled output style** - TTS Summary output style included with the package
-
-### v0.4.0
-- **OpenAI gpt-4o-mini-tts** - New steerable TTS model with `--instructions` option
-- **7 new OpenAI voices** - ash, ballad, coral, sage, verse, marin, cedar (13 total)
-- **ElevenLabs model updated** - Changed from deprecated `eleven_monolingual_v1` to `eleven_multilingual_v2`
-- **Kokoro ONNX 0.5.0** - Updated to latest version
-
-### v0.3.0
-- Major code refactoring with better modularity and code organization
-- New utility modules for shared console, defaults, and HTTP client
-- Test suite with 46 tests for better reliability
-- Documentation synced to match current implementation
-
-### v0.2.2
-- Updated all HTTP requests and downloaders to ignore SSL certificate errors
-- Improves compatibility with corporate proxies and development environments
-
-### v0.2.1
-- Updated dependencies
-- Ensured Python 3.13 compatibility
-
-### v0.2.0
-
-**Major Update**: Configuration files, smarter caching, consistent error handling, and more!
-
-### New Features
-- **Configuration File Support** - Set defaults in `~/.config/par-tts/config.yaml`
-- **Smarter Voice Cache** - Change detection, manual refresh, and voice sample caching
-- **Consistent Error Handling** - Clear error messages with proper exit codes
-- **Multiple Input Methods** - Direct text, stdin piping, and file input (`@filename`)
-- **Volume Control** - Adjust playback volume (0.0 to 5.0) across all platforms (macOS, Linux, Windows)
-- **Voice Preview** - Test voices with sample text before using
+### v0.5.0 (Latest)
+- **Library API surface** -- `import par_tts` is now a proper Python library with
+  `get_provider()`, `list_providers()`, and typed per-provider options.
+  See [Library Usage](#library-usage) for examples.
+- **Import package renamed** -- canonical import is now `par_tts` (was `par_cli_tts`).
+  Old imports still work with a deprecation warning.
+- **Decoupled from Rich** -- library modules use `stdlib logging` instead of Rich
+  console, enabling headless/embedded use without Rich installed.
+- **Audio playback extracted** -- `play_audio_bytes` and `play_audio_with_player`
+  moved to dedicated `par_tts.audio` module.
 
-### Improvements
-- **Enhanced Security** - API key sanitization in debug output
-- **Memory Efficiency** - Stream audio directly to files without buffering
-- **Model Verification** - SHA256 checksum verification for downloads
-- **Better CLI** - All options now have short versions for quick access
-- **Cache Management** - New commands for cache refresh and cleanup
+For the full version history, see [CHANGELOG.md](CHANGELOG.md).
 
 ## Features
 
-- **Multiple TTS Providers** - Support for ElevenLabs, OpenAI, and Kokoro ONNX with easy provider switching
+- **Multiple TTS Providers** - Support for ElevenLabs, OpenAI, Kokoro ONNX, Deepgram (Aura / Aura-2), and Google Gemini with easy provider switching
 - **Configuration File** - Set default preferences in YAML config file (`~/.config/par-tts/config.yaml`)
 - **Flexible Input Methods** - Accept text from command line, stdin pipe, or files (`@filename`)
 - **Voice Name Support** - Use voice names like "Juniper" or "nova" instead of cryptic IDs
@@ -171,6 +145,8 @@ A powerful command-line text-to-speech tool supporting multiple TTS providers (E
 - **ElevenLabs SDK** - Official ElevenLabs API client for high-quality voices
 - **OpenAI SDK** - Official OpenAI API client for TTS
 - **Kokoro ONNX** - Offline TTS with ONNX Runtime for fast inference
+- **Deepgram REST** - Direct httpx integration for Aura / Aura-2 voices (no SDK)
+- **Google Gemini REST** - `generateContent` audio modality with PCM→WAV wrapping (no SDK)
 - **Typer** - Modern CLI framework with automatic help generation
 - **Rich** - Terminal formatting and beautiful output
 - **Pydantic** - Data validation and settings management
@@ -447,25 +423,41 @@ Edit `~/.claude/output-styles/tts-summary.md` to personalize the experience:
 Create a configuration file to set your default preferences:
 
 ```bash
-# Create a sample config file
+# Create a sample config file (prompts before overwriting if one exists)
 par-tts --create-config
 
+# Skip the overwrite prompt with -y / --yes (e.g. for scripted setup)
+par-tts --create-config -y
+
 # Edit the config file
-$EDITOR ~/.config/par-tts/config.yaml
+$EDITOR ~/.config/par-tts/config.yaml      # macOS: ~/Library/Application\ Support/par-tts/config.yaml
 ```
 
 Example configuration file:
 
 ```yaml
-# Default provider (elevenlabs, openai, kokoro-onnx)
+# Default provider (elevenlabs, openai, kokoro-onnx, deepgram, gemini)
 provider: kokoro-onnx
 
-# Default voice
+# Legacy default voice. Only applied when the active provider matches `provider`
+# above — prefer the per-provider `voices:` mapping below for multi-provider use.
 voice: Rachel
 
+# Per-provider default voices (recommended). Each entry is used when that provider
+# is active (via -P/--provider, TTS_PROVIDER, or `provider` above), regardless of
+# which provider this file was originally written for. Takes precedence over `voice`.
+voices:
+  elevenlabs: Juniper
+  openai: nova
+  kokoro-onnx: af_sarah
+  deepgram: aura-2-thalia-en
+  gemini: Kore
+
 # API keys (optional - can also be set via environment variables)
 # elevenlabs_api_key: your-elevenlabs-api-key-here
 # openai_api_key: your-openai-api-key-here
+# deepgram_api_key: your-deepgram-api-key-here
+# gemini_api_key: your-google-gemini-api-key-here
 
 # Output settings
 output_dir: ~/Documents/audio
@@ -484,6 +476,17 @@ play_audio: true
 debug: false
 ```
 
+**Voice resolution order** (highest priority first):
+
+1. CLI `-v` / `--voice` or `TTS_VOICE_ID` env var
+2. `voices.<active-provider>` entry in the config file
+3. The legacy `voice` field, but only when the active provider equals `config.provider`
+4. Provider-specific env var (`ELEVENLABS_VOICE_ID`, `OPENAI_VOICE_ID`, `KOKORO_VOICE_ID`, `DEEPGRAM_VOICE_ID`, `GEMINI_VOICE_ID`)
+5. Built-in provider default
+
+This means switching providers with `-P openai` will pick the right voice for that
+provider — it will not silently inherit a voice ID belonging to a different one.
+
 ### Environment Variables
 
 Create a `.env` file in your project directory with your API keys:
@@ -492,19 +495,23 @@ Create a `.env` file in your project directory with your API keys:
 # Required API keys (at least one for cloud providers)
 ELEVENLABS_API_KEY=your_elevenlabs_key_here
 OPENAI_API_KEY=your_openai_key_here
+DEEPGRAM_API_KEY=your_deepgram_key_here   # DG_API_KEY is also accepted
+GEMINI_API_KEY=your_gemini_key_here       # GOOGLE_API_KEY is also accepted
 
 # Optional: Kokoro ONNX model paths (auto-downloads if not set)
 # Set these only if you want to use custom model locations
 # KOKORO_MODEL_PATH=/path/to/kokoro-v1.0.onnx
 # KOKORO_VOICE_PATH=/path/to/voices-v1.0.bin
 
-# Optional: Default provider (elevenlabs, openai, or kokoro-onnx)
+# Optional: Default provider (elevenlabs, openai, kokoro-onnx, deepgram, or gemini)
 TTS_PROVIDER=kokoro-onnx
 
 # Optional: Default voices
-ELEVENLABS_VOICE_ID=Juniper  # or use voice ID
-OPENAI_VOICE_ID=nova        # alloy, echo, fable, onyx, nova, shimmer
-KOKORO_VOICE_ID=af_sarah    # See available voices with --list
+ELEVENLABS_VOICE_ID=Juniper            # or use voice ID
+OPENAI_VOICE_ID=nova                   # alloy, echo, fable, onyx, nova, shimmer, ...
+KOKORO_VOICE_ID=af_sarah               # See available voices with --list
+DEEPGRAM_VOICE_ID=aura-2-thalia-en     # Aura/Aura-2 model ID (the model IS the voice)
+GEMINI_VOICE_ID=Kore                   # One of 30 prebuilt names (Kore, Zephyr, Aoede, ...)
 
 # Optional: General voice (overrides provider-specific)
 TTS_VOICE_ID=Juniper
@@ -512,6 +519,52 @@ TTS_VOICE_ID=Juniper
 
 ## Usage
 
+### Library Usage
+
+PAR TTS can be used as a Python library in your own projects:
+
+```python
+from par_tts import get_provider, list_providers, Voice
+
+# List available providers
+print(list_providers())
+# ['deepgram', 'elevenlabs', 'gemini', 'kokoro-onnx', 'openai']
+
+# Get a provider class and instantiate it
+KokoroTTS = get_provider("kokoro-onnx")
+provider = KokoroTTS()  # no API key needed for offline providers
+
+# Generate speech
+audio = provider.generate_speech("Hello world", voice="af_sarah")
+
+# Save to file
+provider.save_audio(audio, "output.wav")
+
+# List available voices
+voices: list[Voice] = provider.list_voices()
+for voice in voices:
+    print(f"  {voice.id}: {voice.name}")
+
+# Resolve a voice name to an ID
+voice_id = provider.resolve_voice("sarah")  # partial match -> "af_sarah"
+```
+
+Cloud providers require an API key:
+
+```python
+from par_tts import get_provider
+
+OpenAITTS = get_provider("openai")
+provider = OpenAITTS(api_key="sk-...")
+
+audio = provider.generate_speech(
+    "Hello from OpenAI",
+    voice="nova",
+    speed=1.2,
+)
+provider.save_audio(audio, "greeting.mp3")
+```
+
 ### Quick Start
 
 If installed from PyPI:
@@ -674,7 +727,7 @@ par-tts --refresh-cache --provider elevenlabs
 par-tts --clear-cache-samples --provider elevenlabs
 
 # Or use Makefile commands
-make refresh-cache   # Force refresh voice cache
+make update-cache    # Force refresh voice cache
 make clear-cache     # Clear voice cache including samples
 ```
 
@@ -693,7 +746,7 @@ make clear-cache     # Clear voice cache including samples
 | Option | Short | Description | Default |
 |--------|-------|-------------|---------|
 | `text` | | Text to convert to speech (required) | |
-| `--provider` | `-P` | TTS provider to use (elevenlabs, openai, kokoro-onnx) | kokoro-onnx |
+| `--provider` | `-P` | TTS provider to use (elevenlabs, openai, kokoro-onnx, deepgram, gemini) | kokoro-onnx |
 | `--voice` | `-v` | Voice name or ID to use | Provider default |
 | `--output` | `-o` | Output file path | None (temp file) |
 | `--model` | `-m` | Model to use (provider-specific) | Provider default |
@@ -738,7 +791,8 @@ make clear-cache     # Clear voice cache including samples
 | `--list` | `-l` | List available voices for provider | False |
 | `--preview-voice` | `-V` | Preview a voice with sample text | None |
 | `--list-providers` | `-L` | List available TTS providers | False |
-| `--create-config` | | Create sample configuration file | False |
+| `--create-config` | | Create sample configuration file (prompts before overwriting) | False |
+| `--yes` | `-y` | Skip confirmation prompts (e.g. config overwrite) | False |
 | `--refresh-cache` | | Force refresh voice cache (ElevenLabs) | False |
 | `--clear-cache-samples` | | Clear cached voice samples | False |
 
@@ -805,6 +859,42 @@ make clear-cache     # Clear voice cache including samples
   - No API key needed - runs entirely locally
   - Manual download available via `par-tts-kokoro download`
 
+### Deepgram
+
+- **Models / Voices**: Aura and Aura-2 lines (model and voice are unified — the model
+  parameter *is* the voice). Default: `aura-2-thalia-en`.
+- **Languages**: English, Spanish, Dutch, French, German, Italian, Japanese
+- **Features**:
+  - REST `/v1/speak` integration via httpx (no SDK)
+  - Streaming chunked download — audio writes to file as it arrives
+  - Voice resolution accepts the full ID (`aura-2-thalia-en`), an ID prefix
+    (`aura-2-thalia`), or just the speaker name (`thalia`); name lookup prefers
+    Aura-2 English, then any Aura-2, then Aura-1
+- **Output Formats**: mp3 (default), wav, flac, opus, aac
+- **API key**: `deepgram_api_key` in config, or `DEEPGRAM_API_KEY` /
+  `DG_API_KEY` env var (the historical Deepgram name is also accepted).
+  Get a key at <https://console.deepgram.com>.
+
+### Google Gemini
+
+- **Models**: `gemini-2.5-flash-preview-tts` (default), `gemini-2.5-pro-preview-tts`
+- **Voices**: 30 prebuilt voices with style descriptors — Zephyr (Bright),
+  Puck (Upbeat), Kore (Firm, default), Aoede (Breezy), Fenrir (Excitable),
+  Leda (Youthful), Charon (Informative), Algieba (Smooth), and more.
+  Run `par-tts -P gemini --list` for the full table.
+- **Features**:
+  - REST `generateContent` integration via httpx (no SDK)
+  - Single-shot response (not chunked); the provider wraps the raw 24 kHz
+    16-bit mono PCM in a 44-byte RIFF/WAVE header so output is a self-contained
+    `.wav` file
+  - Voice names are case-insensitive on input (`kore`, `Kore`, and `KORE` all
+    resolve to the canonical `Kore`)
+- **Output Formats**: wav (PCM is the only modality the API emits)
+- **API key**: `gemini_api_key` in config, or one of `GEMINI_API_KEY` /
+  `GOOGLE_API_KEY` env vars. Get a free key at
+  <https://aistudio.google.com/apikey>. (TTS models are currently in preview;
+  rate limits and pricing follow the Gemini API tiers.)
+
 ## Cache Locations
 
 The ElevenLabs voice cache is stored in platform-specific directories:
@@ -869,32 +959,36 @@ make clean       # Clean build artifacts
 
 ```
 par-cli-tts/
-├── src/
-│   ├── __init__.py
-│   ├── tts_cli.py           # Main CLI application
-│   ├── voice_cache.py       # Voice caching system
-│   ├── model_downloader.py  # Kokoro model download manager
-│   ├── utils.py             # Utility functions (streaming, security)
-│   ├── config.py            # Configuration dataclasses
-│   ├── config_file.py       # Configuration file management
-│   ├── errors.py            # Error handling utilities
-│   └── providers/           # TTS provider implementations
+├── par_tts/                     # Library package (pip install par-cli-tts)
+│   ├── __init__.py              # Public API: get_provider, list_providers
+│   ├── audio.py                 # Audio playback utilities
+│   ├── defaults.py              # Default values for providers
+│   ├── errors.py                # TTSError, ErrorType, handle_error
+│   ├── http_client.py           # HTTP client factory
+│   ├── utils.py                 # Streaming, checksums, sanitization
+│   ├── voice_cache.py           # ElevenLabs voice caching
+│   ├── model_downloader.py      # Kokoro ONNX model management
+│   ├── providers/               # TTS provider implementations
+│   │   ├── __init__.py          # PROVIDERS registry
+│   │   ├── base.py              # TTSProvider ABC, Voice, Options
+│   │   ├── elevenlabs.py        # ElevenLabs implementation
+│   │   ├── openai.py            # OpenAI implementation
+│   │   ├── kokoro_onnx.py       # Kokoro ONNX (offline) implementation
+│   │   ├── deepgram.py          # Deepgram implementation
+│   │   └── gemini.py            # Google Gemini implementation
+│   └── cli/                     # CLI-only code (not imported by library users)
 │       ├── __init__.py
-│       ├── base.py          # Abstract base provider
-│       ├── elevenlabs.py    # ElevenLabs implementation
-│       ├── openai.py        # OpenAI implementation
-│       └── kokoro_onnx.py   # Kokoro ONNX implementation
-├── docs/
-│   ├── ARCHITECTURE.md      # System architecture documentation
-│   └── CLAUDE.md            # Development guidelines
-├── .claude/
-│   └── output-styles/
-│       └── tts-summary.md   # Claude Code TTS output style
-├── .env.example             # Example environment file
-├── pyproject.toml           # Project configuration
-├── Makefile                 # Development commands
-├── CLAUDE.md                # AI assistant context
-└── README.md                # This file
+│       ├── tts_cli.py           # Main CLI application
+│       ├── kokoro_cli.py        # Kokoro model management CLI
+│       ├── install_claude_style.py  # Claude Code style installer
+│       ├── config_file.py       # ConfigManager (YAML)
+│       └── console.py           # Rich console instances
+├── par_cli_tts/                 # Compat shim (deprecated, re-exports par_tts)
+├── tests/
+├── pyproject.toml
+├── Makefile
+├── CLAUDE.md
+└── README.md
 ```
 
 ## Troubleshooting