wavoice 0.1.0__tar.gz

wavoice-0.1.0/PKG-INFO

@@ -0,0 +1,254 @@
+Metadata-Version: 2.3
+Name: wavoice
+Version: 0.1.0
+Summary: One-command WhatsApp Voice AI with Pipecat and automated Cloudflare Quick Tunnels
+Author: Amit Bhakt
+Author-email: Amit Bhakt <yashubhakt@gmail.com>
+Requires-Dist: aiohttp>=3.14.5
+Requires-Dist: fastapi>=0.143.0
+Requires-Dist: loguru>=0.7.3
+Requires-Dist: pipecat-ai[google,webrtc]>=1.12.0
+Requires-Dist: pydantic>=2.14.1
+Requires-Dist: pydantic-settings>=2.15.0
+Requires-Dist: python-dotenv>=1.2.4
+Requires-Dist: rich>=15.0.0
+Requires-Dist: typer>=0.27.3
+Requires-Dist: uvicorn[standard]>=0.54.0
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+
+# WAVoice: Set Up WhatsApp Voice AI in 90 Seconds
+
+[![Python 3.12](https://img.shields.io/badge/python-3.12-blue.svg)](https://www.python.org/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Powered by Pipecat](https://img.shields.io/badge/powered%20by-Pipecat-green.svg)](https://github.com/pipecat-ai/pipecat)
+[![Author: Amit Bhakt](https://img.shields.io/badge/creator-Amit%20Bhakt-orange.svg)](https://github.com/amitbhakt)
+
+> **The zero-friction, one-command pipeline for WhatsApp Voice AI.**  
+> Go from zero to an active AI voice agent answering live WhatsApp calls in under **90 seconds**. No manual Meta dashboard clicking, no ngrok account setup, and no WebRTC configuration required.
+
+Created by [Amit Bhakt](https://github.com/amitbhakt), `WAVoice` solves the hardest part of building WhatsApp voice agents: **the entire telephony and networking plumbing**.
+
+---
+
+## Why Developers Use WAVoice
+
+Setting up WhatsApp voice calling traditionally requires hours of manual work: navigating Meta Business Manager, registering phone number IDs, manually creating ngrok tunnels, pasting webhook verification tokens, handling WebRTC SDP offer/answers, and diagnosing why audio drops over NAT.
+
+**`WAVoice` collapses all of that into a single 90-second command (`wavoice init`):**
+
+1. **Automated Cloudflare Quick Tunnel**: Ephemeral public HTTPS TLS gateway with zero tokens or account sign-ups.
+2. **Auto-Discovery**: Extracts your WABA ID and Phone Number ID directly from your token via Meta Graph API.
+3. **Programmatic Calling Activation**: Enables WhatsApp Voice Calling and makes the Call button visible automatically.
+4. **Full 3-Tier Webhook Sync**: Programmatically configures Phone Number overrides, WABA subscriptions, and App subscriptions.
+5. **Production WebRTC Infrastructure**: Pre-configured STUN/TURN, SRTP audio handling, and atomic call claim locks (preventing duplicate webhook deliveries).
+
+---
+
+## How It Works: Instant Testing vs. Custom Pipelines
+
+Whether you want a complete out-of-the-box agent or a custom multi-model architecture, `WAVoice` separates the **telephony infrastructure** from your **AI logic**:
+
+```
+                       ┌────────────────────────────────────────┐
+                       │  Telephony Infrastructure Layer        │
+                       │  (Handled automatically by WAVoice)    │
+                       │                                        │
+                       │  - Cloudflare Quick Tunnel             │
+                       │  - Meta Graph API Webhooks             │
+                       │  - WebRTC SDP Offer / Answer           │
+                       │  - SRTP Audio Stream Decoupling        │
+                       └───────────────────┬────────────────────┘
+                                           │
+                       ┌───────────────────┴────────────────────┐
+                       ▼                                        ▼
+      ┌─────────────────────────────────┐      ┌─────────────────────────────────┐
+      │  Mode A: Out-of-the-Box (90s)   │      │  Mode B: Custom Layers          │
+      │                                 │      │  (Pluggable Pipecat Pipeline)   │
+      │  Run: `wavoice start`           │      │                                 │
+      │  Native Speech-to-Speech via    │      │  - STT: Deepgram, Whisper, Groq │
+      │  Gemini 2.0 Flash Live          │      │  - LLM: OpenAI, Claude, Ollama  │
+      │  (~300ms latency, zero code)    │      │  - TTS: Cartesia, ElevenLabs    │
+      └─────────────────────────────────┘      └─────────────────────────────────┘
+```
+
+### How does the one-command setup help developers who want separate layers?
+When you want to build a cascaded stack (**STT $\rightarrow$ LLM $\rightarrow$ TTS**), you still face the exact same frustrating hurdle: connecting WhatsApp's WebRTC audio stream to your server. 
+
+By running `wavoice init`, **your WhatsApp number and webhook plumbing are 100% configured in 90 seconds**. Then, instead of maintaining complex SIP/WebRTC servers, you simply write standard, modular Python:
+
+```python
+from wavoice import WhatsAppVoiceApp
+
+app = WhatsAppVoiceApp()
+
+@app.on_call
+async def handle_call(transport, call_info):
+    # 'transport' already receives raw audio from WhatsApp WebRTC
+    # Plug in any separate STT, LLM, or TTS processor:
+    pipeline = Pipeline([
+        transport.input(),
+        DeepgramSTTService(...),
+        OpenAILLMService(...),
+        CartesiaTTSService(...),
+        transport.output(),
+    ])
+    ...
+```
+
+---
+
+## 90-Second Quickstart
+
+### Step 1: Install
+```bash
+git clone https://github.com/amitbhakt/wavoice.git
+cd wavoice
+uv sync
+```
+*(Or install via `pip install wavoice`)*
+
+### Step 2: One-Command Setup
+```bash
+uv run wavoice init
+```
+
+The interactive wizard asks for only 3 credentials:
+1. `WHATSAPP_TOKEN`: Meta System User access token.
+2. `WHATSAPP_APP_SECRET`: Meta App Secret.
+3. `GEMINI_API_KEY`: Google Gemini API key.
+
+`WAVoice` automatically discovers your business accounts, activates WhatsApp voice calling, saves `.env`, and starts the server immediately.
+
+### Step 3: Dial & Talk
+Open WhatsApp on your phone and dial your business number. Your AI agent answers immediately.
+
+---
+
+## Pre-Flight Diagnostics
+
+To inspect your setup, token scopes, voice calling flags, and webhook routing tiers at any time:
+
+```bash
+uv run wavoice doctor
+```
+
+Output:
+```text
+╦ ╦╔═╗╦  ╦╔═╗╦╔═╗╔═╗   WAVoice v0.1.0
+║║║╠═╣╚╗╔╝║ ║║║  ║╣    One-command WhatsApp Voice AI runtime
+╚╩╝╩ ╩ ╚╝ ╚═╝╩╚═╝╚═╝
+
+╭────────────────────────────────╮
+│ WAVoice Pre-Flight Diagnostics │
+╰────────────────────────────────╯
+┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
+┃ Check                          ┃ Status       ┃ Details                      ┃
+┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
+│ Meta Credentials               │ PASS         │ Token & Phone ID configured  │
+│ Phone Number Reachability      │ PASS         │ Verified number: +1 555-188  │
+│ WhatsApp Voice Calling API     │ PASS         │ Voice calling is ENABLED     │
+│ Tier 1: Phone Override         │ ACTIVE       │ Cloudflare Tunnel Verified   │
+│ Tier 2: WABA Subscription      │ ACTIVE       │ Webhook Subscribed           │
+│ Tier 3: App Subscriptions      │ ACTIVE       │ calls, messages Active       │
+│ Default AI Agent               │ PASS         │ Gemini 2.0 Flash Live ready  │
+└────────────────────────────────┴──────────────┴──────────────────────────────┘
+```
+
+---
+
+## Building Custom Multi-Model Pipelines
+
+For developers building with independent STT, LLM, and TTS providers, `WAVoice` exposes the complete [Pipecat](https://github.com/pipecat-ai/pipecat) pipeline:
+
+```python
+import os
+from wavoice import WhatsAppVoiceApp
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.cartesia import CartesiaTTSService
+
+app = WhatsAppVoiceApp()
+
+@app.on_call
+async def handle_incoming_call(transport, call_info):
+    caller = getattr(call_info, "from_", "caller")
+    print(f"Incoming call from {caller}")
+
+    # 1. Custom Layer Services
+    stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
+    llm = OpenAILLMService(api_key=os.environ["OPENAI_API_KEY"], model="gpt-4o-mini")
+    tts = CartesiaTTSService(api_key=os.environ["CARTESIA_API_KEY"], voice_id="...")
+
+    # 2. Context Aggregation & Silero Turn Detection
+    context = LLMContext([{"role": "system", "content": "You are a concise voice assistant."}])
+    user_agg, assistant_agg = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
+
+    # 3. Assemble Pipeline
+    pipeline = Pipeline([
+        transport.input(),    # WebRTC Audio In from WhatsApp
+        stt,                  # Speech-to-Text
+        user_agg,             # Turn Aggregator
+        llm,                  # Large Language Model
+        tts,                  # Text-to-Speech
+        transport.output(),   # WebRTC Audio Out to WhatsApp
+        assistant_agg,
+    ])
+
+    task = PipelineTask(pipeline=pipeline, params=PipelineParams(allow_interruptions=True))
+    runner = PipelineRunner()
+    await runner.run(task)
+
+if __name__ == "__main__":
+    app.run()  # Launches tunnel, registers Meta webhooks, and serves pipeline
+```
+
+*(See [examples/custom_stt_llm_tts.py](examples/custom_stt_llm_tts.py) for the complete runnable file)*
+
+---
+
+## CLI Command Reference
+
+| Command | Description |
+| :--- | :--- |
+| `wavoice init` | Complete 90-second setup: prompts for 3 credentials, auto-discovers IDs, turns on voice calling, and launches. Pass `--no-telemetry` to opt out of usage metrics. |
+| `wavoice doctor` | Runs diagnostics across Meta credentials, calling status, and 3-tier webhooks. |
+| `wavoice start` | Starts the server, establishes the Cloudflare tunnel, and begins accepting calls. Pass `--no-telemetry` to run with telemetry disabled. |
+
+---
+
+## Technical Details
+
+- **WebRTC Protocol**: WhatsApp Calling exchanges SDP offers/answers over HTTPS and streams media via SRTP over UDP. `WAVoice` uses `aiortc` and Pipecat's `SmallWebRTCTransport` to negotiate codecs and stream PCM audio.
+- **Webhook Delivery Deduplication**: Meta delivers webhooks at least once, causing race conditions where multiple workers answer the same call. `WAVoice` uses atomic in-memory claiming per `call_id` to guarantee calls are answered exactly once.
+- **Bi-directional Termination**: If the caller hangs up, `WAVoice` tears down the pipeline. If the bot hangs up or times out, `WAVoice` calls `POST /v21.0/{phone_number_id}/calls` with `action: "terminate"` to end the call on the user's phone.
+- **Telemetry & Privacy**: WAVoice collects anonymous usage metrics (command runs, answered calls, and coarse country/timezone) to improve SDK stability. No personal info, phone numbers, tokens, or audio data are ever collected. Telemetry is enabled by default, and you can opt out at any time by:
+  - Running `wavoice init --no-telemetry` or `wavoice start --no-telemetry`
+  - Setting `WAVOICE_TELEMETRY=false` in `.env`
+  - Setting `DO_NOT_TRACK=1` in your environment
+
+---
+
+## Maintainer & Credits
+
+Crafted by **Amit Bhakt** ([@amitbhakt](https://github.com/amitbhakt)).
+
+Contributions, issues, and feature suggestions are welcome on GitHub at [https://github.com/amitbhakt/wavoice](https://github.com/amitbhakt/wavoice).
+
+---
+
+## License
+
+MIT License. Copyright (c) 2026 Amit Bhakt.

wavoice-0.1.0/README.md

@@ -0,0 +1,235 @@
+# WAVoice: Set Up WhatsApp Voice AI in 90 Seconds
+
+[![Python 3.12](https://img.shields.io/badge/python-3.12-blue.svg)](https://www.python.org/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Powered by Pipecat](https://img.shields.io/badge/powered%20by-Pipecat-green.svg)](https://github.com/pipecat-ai/pipecat)
+[![Author: Amit Bhakt](https://img.shields.io/badge/creator-Amit%20Bhakt-orange.svg)](https://github.com/amitbhakt)
+
+> **The zero-friction, one-command pipeline for WhatsApp Voice AI.**  
+> Go from zero to an active AI voice agent answering live WhatsApp calls in under **90 seconds**. No manual Meta dashboard clicking, no ngrok account setup, and no WebRTC configuration required.
+
+Created by [Amit Bhakt](https://github.com/amitbhakt), `WAVoice` solves the hardest part of building WhatsApp voice agents: **the entire telephony and networking plumbing**.
+
+---
+
+## Why Developers Use WAVoice
+
+Setting up WhatsApp voice calling traditionally requires hours of manual work: navigating Meta Business Manager, registering phone number IDs, manually creating ngrok tunnels, pasting webhook verification tokens, handling WebRTC SDP offer/answers, and diagnosing why audio drops over NAT.
+
+**`WAVoice` collapses all of that into a single 90-second command (`wavoice init`):**
+
+1. **Automated Cloudflare Quick Tunnel**: Ephemeral public HTTPS TLS gateway with zero tokens or account sign-ups.
+2. **Auto-Discovery**: Extracts your WABA ID and Phone Number ID directly from your token via Meta Graph API.
+3. **Programmatic Calling Activation**: Enables WhatsApp Voice Calling and makes the Call button visible automatically.
+4. **Full 3-Tier Webhook Sync**: Programmatically configures Phone Number overrides, WABA subscriptions, and App subscriptions.
+5. **Production WebRTC Infrastructure**: Pre-configured STUN/TURN, SRTP audio handling, and atomic call claim locks (preventing duplicate webhook deliveries).
+
+---
+
+## How It Works: Instant Testing vs. Custom Pipelines
+
+Whether you want a complete out-of-the-box agent or a custom multi-model architecture, `WAVoice` separates the **telephony infrastructure** from your **AI logic**:
+
+```
+                       ┌────────────────────────────────────────┐
+                       │  Telephony Infrastructure Layer        │
+                       │  (Handled automatically by WAVoice)    │
+                       │                                        │
+                       │  - Cloudflare Quick Tunnel             │
+                       │  - Meta Graph API Webhooks             │
+                       │  - WebRTC SDP Offer / Answer           │
+                       │  - SRTP Audio Stream Decoupling        │
+                       └───────────────────┬────────────────────┘
+                                           │
+                       ┌───────────────────┴────────────────────┐
+                       ▼                                        ▼
+      ┌─────────────────────────────────┐      ┌─────────────────────────────────┐
+      │  Mode A: Out-of-the-Box (90s)   │      │  Mode B: Custom Layers          │
+      │                                 │      │  (Pluggable Pipecat Pipeline)   │
+      │  Run: `wavoice start`           │      │                                 │
+      │  Native Speech-to-Speech via    │      │  - STT: Deepgram, Whisper, Groq │
+      │  Gemini 2.0 Flash Live          │      │  - LLM: OpenAI, Claude, Ollama  │
+      │  (~300ms latency, zero code)    │      │  - TTS: Cartesia, ElevenLabs    │
+      └─────────────────────────────────┘      └─────────────────────────────────┘
+```
+
+### How does the one-command setup help developers who want separate layers?
+When you want to build a cascaded stack (**STT $\rightarrow$ LLM $\rightarrow$ TTS**), you still face the exact same frustrating hurdle: connecting WhatsApp's WebRTC audio stream to your server. 
+
+By running `wavoice init`, **your WhatsApp number and webhook plumbing are 100% configured in 90 seconds**. Then, instead of maintaining complex SIP/WebRTC servers, you simply write standard, modular Python:
+
+```python
+from wavoice import WhatsAppVoiceApp
+
+app = WhatsAppVoiceApp()
+
+@app.on_call
+async def handle_call(transport, call_info):
+    # 'transport' already receives raw audio from WhatsApp WebRTC
+    # Plug in any separate STT, LLM, or TTS processor:
+    pipeline = Pipeline([
+        transport.input(),
+        DeepgramSTTService(...),
+        OpenAILLMService(...),
+        CartesiaTTSService(...),
+        transport.output(),
+    ])
+    ...
+```
+
+---
+
+## 90-Second Quickstart
+
+### Step 1: Install
+```bash
+git clone https://github.com/amitbhakt/wavoice.git
+cd wavoice
+uv sync
+```
+*(Or install via `pip install wavoice`)*
+
+### Step 2: One-Command Setup
+```bash
+uv run wavoice init
+```
+
+The interactive wizard asks for only 3 credentials:
+1. `WHATSAPP_TOKEN`: Meta System User access token.
+2. `WHATSAPP_APP_SECRET`: Meta App Secret.
+3. `GEMINI_API_KEY`: Google Gemini API key.
+
+`WAVoice` automatically discovers your business accounts, activates WhatsApp voice calling, saves `.env`, and starts the server immediately.
+
+### Step 3: Dial & Talk
+Open WhatsApp on your phone and dial your business number. Your AI agent answers immediately.
+
+---
+
+## Pre-Flight Diagnostics
+
+To inspect your setup, token scopes, voice calling flags, and webhook routing tiers at any time:
+
+```bash
+uv run wavoice doctor
+```
+
+Output:
+```text
+╦ ╦╔═╗╦  ╦╔═╗╦╔═╗╔═╗   WAVoice v0.1.0
+║║║╠═╣╚╗╔╝║ ║║║  ║╣    One-command WhatsApp Voice AI runtime
+╚╩╝╩ ╩ ╚╝ ╚═╝╩╚═╝╚═╝
+
+╭────────────────────────────────╮
+│ WAVoice Pre-Flight Diagnostics │
+╰────────────────────────────────╯
+┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
+┃ Check                          ┃ Status       ┃ Details                      ┃
+┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
+│ Meta Credentials               │ PASS         │ Token & Phone ID configured  │
+│ Phone Number Reachability      │ PASS         │ Verified number: +1 555-188  │
+│ WhatsApp Voice Calling API     │ PASS         │ Voice calling is ENABLED     │
+│ Tier 1: Phone Override         │ ACTIVE       │ Cloudflare Tunnel Verified   │
+│ Tier 2: WABA Subscription      │ ACTIVE       │ Webhook Subscribed           │
+│ Tier 3: App Subscriptions      │ ACTIVE       │ calls, messages Active       │
+│ Default AI Agent               │ PASS         │ Gemini 2.0 Flash Live ready  │
+└────────────────────────────────┴──────────────┴──────────────────────────────┘
+```
+
+---
+
+## Building Custom Multi-Model Pipelines
+
+For developers building with independent STT, LLM, and TTS providers, `WAVoice` exposes the complete [Pipecat](https://github.com/pipecat-ai/pipecat) pipeline:
+
+```python
+import os
+from wavoice import WhatsAppVoiceApp
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.cartesia import CartesiaTTSService
+
+app = WhatsAppVoiceApp()
+
+@app.on_call
+async def handle_incoming_call(transport, call_info):
+    caller = getattr(call_info, "from_", "caller")
+    print(f"Incoming call from {caller}")
+
+    # 1. Custom Layer Services
+    stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
+    llm = OpenAILLMService(api_key=os.environ["OPENAI_API_KEY"], model="gpt-4o-mini")
+    tts = CartesiaTTSService(api_key=os.environ["CARTESIA_API_KEY"], voice_id="...")
+
+    # 2. Context Aggregation & Silero Turn Detection
+    context = LLMContext([{"role": "system", "content": "You are a concise voice assistant."}])
+    user_agg, assistant_agg = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
+
+    # 3. Assemble Pipeline
+    pipeline = Pipeline([
+        transport.input(),    # WebRTC Audio In from WhatsApp
+        stt,                  # Speech-to-Text
+        user_agg,             # Turn Aggregator
+        llm,                  # Large Language Model
+        tts,                  # Text-to-Speech
+        transport.output(),   # WebRTC Audio Out to WhatsApp
+        assistant_agg,
+    ])
+
+    task = PipelineTask(pipeline=pipeline, params=PipelineParams(allow_interruptions=True))
+    runner = PipelineRunner()
+    await runner.run(task)
+
+if __name__ == "__main__":
+    app.run()  # Launches tunnel, registers Meta webhooks, and serves pipeline
+```
+
+*(See [examples/custom_stt_llm_tts.py](examples/custom_stt_llm_tts.py) for the complete runnable file)*
+
+---
+
+## CLI Command Reference
+
+| Command | Description |
+| :--- | :--- |
+| `wavoice init` | Complete 90-second setup: prompts for 3 credentials, auto-discovers IDs, turns on voice calling, and launches. Pass `--no-telemetry` to opt out of usage metrics. |
+| `wavoice doctor` | Runs diagnostics across Meta credentials, calling status, and 3-tier webhooks. |
+| `wavoice start` | Starts the server, establishes the Cloudflare tunnel, and begins accepting calls. Pass `--no-telemetry` to run with telemetry disabled. |
+
+---
+
+## Technical Details
+
+- **WebRTC Protocol**: WhatsApp Calling exchanges SDP offers/answers over HTTPS and streams media via SRTP over UDP. `WAVoice` uses `aiortc` and Pipecat's `SmallWebRTCTransport` to negotiate codecs and stream PCM audio.
+- **Webhook Delivery Deduplication**: Meta delivers webhooks at least once, causing race conditions where multiple workers answer the same call. `WAVoice` uses atomic in-memory claiming per `call_id` to guarantee calls are answered exactly once.
+- **Bi-directional Termination**: If the caller hangs up, `WAVoice` tears down the pipeline. If the bot hangs up or times out, `WAVoice` calls `POST /v21.0/{phone_number_id}/calls` with `action: "terminate"` to end the call on the user's phone.
+- **Telemetry & Privacy**: WAVoice collects anonymous usage metrics (command runs, answered calls, and coarse country/timezone) to improve SDK stability. No personal info, phone numbers, tokens, or audio data are ever collected. Telemetry is enabled by default, and you can opt out at any time by:
+  - Running `wavoice init --no-telemetry` or `wavoice start --no-telemetry`
+  - Setting `WAVOICE_TELEMETRY=false` in `.env`
+  - Setting `DO_NOT_TRACK=1` in your environment
+
+---
+
+## Maintainer & Credits
+
+Crafted by **Amit Bhakt** ([@amitbhakt](https://github.com/amitbhakt)).
+
+Contributions, issues, and feature suggestions are welcome on GitHub at [https://github.com/amitbhakt/wavoice](https://github.com/amitbhakt/wavoice).
+
+---
+
+## License
+
+MIT License. Copyright (c) 2026 Amit Bhakt.

wavoice-0.1.0/pyproject.toml

@@ -0,0 +1,36 @@
+[project]
+name = "wavoice"
+version = "0.1.0"
+description = "One-command WhatsApp Voice AI with Pipecat and automated Cloudflare Quick Tunnels"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "aiohttp>=3.14.5",
+    "fastapi>=0.143.0",
+    "loguru>=0.7.3",
+    "pipecat-ai[google,webrtc]>=1.12.0",
+    "pydantic>=2.14.1",
+    "pydantic-settings>=2.15.0",
+    "python-dotenv>=1.2.4",
+    "rich>=15.0.0",
+    "typer>=0.27.3",
+    "uvicorn[standard]>=0.54.0",
+]
+
+[[project.authors]]
+name = "Amit Bhakt"
+email = "yashubhakt@gmail.com"
+
+[project.scripts]
+wavoice = "wavoice.cli:cli"
+
+[build-system]
+requires = ["uv_build>=0.12.13,<0.13.0"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = [
+    "httpx>=0.28.1",
+    "pytest>=9.1.1",
+    "pytest-asyncio>=1.4.0",
+]

wavoice-0.1.0/pyproject.toml.orig

@@ -0,0 +1,35 @@
+[project]
+name = "wavoice"
+version = "0.1.0"
+description = "One-command WhatsApp Voice AI with Pipecat and automated Cloudflare Quick Tunnels"
+readme = "README.md"
+authors = [
+    { name = "Amit Bhakt", email = "yashubhakt@gmail.com" }
+]
+requires-python = ">=3.12"
+dependencies = [
+    "aiohttp>=3.14.5",
+    "fastapi>=0.143.0",
+    "loguru>=0.7.3",
+    "pipecat-ai[google,webrtc]>=1.12.0",
+    "pydantic>=2.14.1",
+    "pydantic-settings>=2.15.0",
+    "python-dotenv>=1.2.4",
+    "rich>=15.0.0",
+    "typer>=0.27.3",
+    "uvicorn[standard]>=0.54.0",
+]
+
+[project.scripts]
+wavoice = "wavoice.cli:cli"
+
+[build-system]
+requires = ["uv_build>=0.12.13,<0.13.0"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = [
+    "httpx>=0.28.1",
+    "pytest>=9.1.1",
+    "pytest-asyncio>=1.4.0",
+]

wavoice-0.1.0/src/wavoice/__init__.py

@@ -0,0 +1,7 @@
+"""wa-voice: One-command WhatsApp Voice AI with Pipecat."""
+
+from wavoice.core.config import Settings, settings
+from wavoice.sdk import WhatsAppVoiceApp
+
+__version__ = "0.1.0"
+__all__ = ["WhatsAppVoiceApp", "Settings", "settings"]