pipecat-ai-typecast 0.0.1__tar.gz

pipecat_ai_typecast-0.0.1/.gitignore

@@ -0,0 +1,6 @@
+__pycache__/
+
+*.egg-info/
+dist/
+build/
+.env

pipecat_ai_typecast-0.0.1/CHANGELOG.md

@@ -0,0 +1,16 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.0.1] - 2025-11-12
+
+### Added
+- Initial release of Typecast TTS integration for Pipecat
+- `TypecastTTSService` for high-quality TTS service
+
+### Documentation
+- README with installation and usage instructions
+- Foundational example demonstrating complete pipecat bot setup

pipecat_ai_typecast-0.0.1/LICENSE

@@ -0,0 +1,24 @@
+BSD 2-Clause License
+
+Copyright (c) 2024–2025, Daily
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

pipecat_ai_typecast-0.0.1/PKG-INFO

@@ -0,0 +1,152 @@
+Metadata-Version: 2.4
+Name: pipecat-ai-typecast
+Version: 0.0.1
+Summary: Typecast is an AI text-to-speech API that converts text into lifelike, expressive speech in many languages.
+Author-email: Neosapience <help@typecast.ai>
+Maintainer-email: Neosapience <help@typecast.ai>
+License-Expression: BSD-2-Clause
+Project-URL: Homepage, https://typecast.ai
+Project-URL: Documentation, https://typecast.ai/docs/overview
+Project-URL: Source, https://github.com/neosapience/pipecat-typecast
+Keywords: pipecat,text-to-speech,ai
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pipecat-ai>=0.0.94
+Requires-Dist: aiohttp>=3.9.0
+Requires-Dist: loguru>=0.7.0
+Requires-Dist: pydantic>=2.0.0
+Dynamic: license-file
+
+# Pipecat Typecast TTS Integration
+
+Add high-quality neural voices from [Typecast](https://typecast.ai/) to your Pipecat AI pipelines.
+
+**Maintainer:** Neosapience / Typecast team (@neosapience)
+
+## Installation
+
+```bash
+pip install pipecat-ai-typecast
+```
+
+## Prerequisites
+
+- Typecast API key (`TYPECAST_API_KEY`)
+- Optional: Voice override (`TYPECAST_VOICE_ID`) – defaults to `tc_62a8975e695ad26f7fb514d1`
+
+## Usage with Pipecat Pipeline
+
+`TypecastTTSService` integrates Typecast's streaming text-to-speech into a Pipecat pipeline. It converts LLM text output into expressive speech while leveraging Pipecat's transport, STT, and turn-taking stack.
+
+```python
+import os, aiohttp
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat_typecast.tts import TypecastTTSService
+
+async with aiohttp.ClientSession() as session:
+    llm = ...
+    sst = ...
+    tts = TypecastTTSService(
+        aiohttp_session=session,
+        api_key=os.getenv("TYPECAST_API_KEY"),
+        voice_id=os.getenv("TYPECAST_VOICE_ID", "tc_62a8975e695ad26f7fb514d1"),
+    )
+
+    pipeline = Pipeline([
+        transport.input(),               # audio/user input
+        stt,                             # speech to text
+        context_aggregator.user(),       # add user text to context
+        llm,                             # LLM generates response
+        tts,                             # Typecast TTS synthesis
+        transport.output(),              # stream audio back to user
+        context_aggregator.assistant(),  # store assistant response
+    ])
+```
+
+See [`example.py`](example.py) for a complete working example including event handlers and transport setup.
+
+### Advanced Configuration (Emotion & Audio Controls)
+
+`TypecastTTSService` exposes structured parameter models so you can tune emotion and audio output.
+
+```python
+from pipecat_typecast.tts import (
+    TypecastTTSService,
+    TypecastInputParams,
+    PromptOptions,
+    OutputOptions,
+)
+
+params = TypecastInputParams(
+    # Language influences pronunciation model (defaults to English)
+    # Language.EN / Language.KO / Language.JA ...
+    # If omitted, Typecast auto-detect may apply (depending on voice).
+    prompt_options=PromptOptions(
+        emotion_preset="happy",      # normal | happy | sad | angry | whisper (voice dependent)
+        emotion_intensity=1.3,       # 0.0–2.0 (float)
+    ),
+    output_options=OutputOptions(
+        volume=110,                  # 0–200 (percent)
+        audio_pitch=2,               # -12..12 (semitones)
+        audio_tempo=1.05,            # 0.5–2.0 (playback speed)
+        audio_format="wav",          # Only 'wav' currently supported
+    ),
+)
+
+tts = TypecastTTSService(
+    aiohttp_session=session,
+    api_key=os.getenv("TYPECAST_API_KEY"),
+    voice_id="tc_62a8975e695ad26f7fb514d1",  # Replace with another voice ID as desired
+    model="ssfm-v21",                        # Default model
+    params=params,
+)
+```
+
+Notes:
+- `emotion_preset` availability varies by voice. If unsupported, the service falls back to neutral.
+- `emotion_intensity` > 1.0 increases expressiveness; extreme values can sound synthetic.
+- `audio_pitch` shifts pitch in musical semitone units (use small adjustments for naturalness).
+- `audio_tempo` changes speaking speed; keep within 0.85–1.15 for intelligibility.
+- `seed` (set in `TypecastInputParams`) provides deterministic synthesis for identical text (when supported by model).
+- Unsupported `audio_format` values yield an error frame—keep `wav`.
+
+## Running the Example
+
+1. Install dependencies:
+    ```bash
+    uv sync
+    ```
+
+2. Set up your environment
+
+   ```bash
+   cp env.example .env
+   ```
+
+3. Run:
+    ```bash
+    uv run python example.py
+    ```
+
+The bot will create a call (e.g. Daily room) and speak responses using Typecast voices.
+
+## Compatibility
+
+**Tested with Pipecat v0.0.89**
+
+- Python 3.10+
+- Daily / Twilio / generic WebRTC transports (see `example.py`)
+
+## License
+
+BSD-2-Clause - see [LICENSE](LICENSE)
+
+## Support
+
+- Docs: https://typecast.ai (refer to API docs for voice IDs & parameters)
+- Pipecat Discord: https://discord.gg/pipecat (`#community-integrations`)

pipecat_ai_typecast-0.0.1/README.md

@@ -0,0 +1,128 @@
+# Pipecat Typecast TTS Integration
+
+Add high-quality neural voices from [Typecast](https://typecast.ai/) to your Pipecat AI pipelines.
+
+**Maintainer:** Neosapience / Typecast team (@neosapience)
+
+## Installation
+
+```bash
+pip install pipecat-ai-typecast
+```
+
+## Prerequisites
+
+- Typecast API key (`TYPECAST_API_KEY`)
+- Optional: Voice override (`TYPECAST_VOICE_ID`) – defaults to `tc_62a8975e695ad26f7fb514d1`
+
+## Usage with Pipecat Pipeline
+
+`TypecastTTSService` integrates Typecast's streaming text-to-speech into a Pipecat pipeline. It converts LLM text output into expressive speech while leveraging Pipecat's transport, STT, and turn-taking stack.
+
+```python
+import os, aiohttp
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat_typecast.tts import TypecastTTSService
+
+async with aiohttp.ClientSession() as session:
+    llm = ...
+    sst = ...
+    tts = TypecastTTSService(
+        aiohttp_session=session,
+        api_key=os.getenv("TYPECAST_API_KEY"),
+        voice_id=os.getenv("TYPECAST_VOICE_ID", "tc_62a8975e695ad26f7fb514d1"),
+    )
+
+    pipeline = Pipeline([
+        transport.input(),               # audio/user input
+        stt,                             # speech to text
+        context_aggregator.user(),       # add user text to context
+        llm,                             # LLM generates response
+        tts,                             # Typecast TTS synthesis
+        transport.output(),              # stream audio back to user
+        context_aggregator.assistant(),  # store assistant response
+    ])
+```
+
+See [`example.py`](example.py) for a complete working example including event handlers and transport setup.
+
+### Advanced Configuration (Emotion & Audio Controls)
+
+`TypecastTTSService` exposes structured parameter models so you can tune emotion and audio output.
+
+```python
+from pipecat_typecast.tts import (
+    TypecastTTSService,
+    TypecastInputParams,
+    PromptOptions,
+    OutputOptions,
+)
+
+params = TypecastInputParams(
+    # Language influences pronunciation model (defaults to English)
+    # Language.EN / Language.KO / Language.JA ...
+    # If omitted, Typecast auto-detect may apply (depending on voice).
+    prompt_options=PromptOptions(
+        emotion_preset="happy",      # normal | happy | sad | angry | whisper (voice dependent)
+        emotion_intensity=1.3,       # 0.0–2.0 (float)
+    ),
+    output_options=OutputOptions(
+        volume=110,                  # 0–200 (percent)
+        audio_pitch=2,               # -12..12 (semitones)
+        audio_tempo=1.05,            # 0.5–2.0 (playback speed)
+        audio_format="wav",          # Only 'wav' currently supported
+    ),
+)
+
+tts = TypecastTTSService(
+    aiohttp_session=session,
+    api_key=os.getenv("TYPECAST_API_KEY"),
+    voice_id="tc_62a8975e695ad26f7fb514d1",  # Replace with another voice ID as desired
+    model="ssfm-v21",                        # Default model
+    params=params,
+)
+```
+
+Notes:
+- `emotion_preset` availability varies by voice. If unsupported, the service falls back to neutral.
+- `emotion_intensity` > 1.0 increases expressiveness; extreme values can sound synthetic.
+- `audio_pitch` shifts pitch in musical semitone units (use small adjustments for naturalness).
+- `audio_tempo` changes speaking speed; keep within 0.85–1.15 for intelligibility.
+- `seed` (set in `TypecastInputParams`) provides deterministic synthesis for identical text (when supported by model).
+- Unsupported `audio_format` values yield an error frame—keep `wav`.
+
+## Running the Example
+
+1. Install dependencies:
+    ```bash
+    uv sync
+    ```
+
+2. Set up your environment
+
+   ```bash
+   cp env.example .env
+   ```
+
+3. Run:
+    ```bash
+    uv run python example.py
+    ```
+
+The bot will create a call (e.g. Daily room) and speak responses using Typecast voices.
+
+## Compatibility
+
+**Tested with Pipecat v0.0.89**
+
+- Python 3.10+
+- Daily / Twilio / generic WebRTC transports (see `example.py`)
+
+## License
+
+BSD-2-Clause - see [LICENSE](LICENSE)
+
+## Support
+
+- Docs: https://typecast.ai (refer to API docs for voice IDs & parameters)
+- Pipecat Discord: https://discord.gg/pipecat (`#community-integrations`)

pipecat_ai_typecast-0.0.1/env.example

@@ -0,0 +1,9 @@
+DEEPGRAM_API_KEY=...
+
+OPENAI_API_KEY=...
+
+CARTESIA_API_KEY=...
+
+DAILY_API_KEY=...
+
+TYPECAST_API_KEY=...

pipecat_ai_typecast-0.0.1/example.py

@@ -0,0 +1,144 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+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
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+from pipecat_typecast import TypecastTTSService
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info("Starting bot")
+
+    async with aiohttp.ClientSession() as session:
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        typecast_kwargs = {}
+        voice_id = os.getenv("TYPECAST_VOICE_ID")
+        if voice_id:
+            typecast_kwargs["voice_id"] = voice_id
+
+        tts = TypecastTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("TYPECAST_API_KEY", ""),
+            **typecast_kwargs,
+        )
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+        messages = [
+            {
+                "role": "system",
+                "content": (
+                    "You are a helpful LLM in a WebRTC call. "
+                    "Your goal is to demonstrate your capabilities succinctly. "
+                    "Your output will be converted to audio, so avoid special characters."
+                ),
+            },
+        ]
+
+        context = LLMContext(messages)
+        context_aggregator = LLMContextAggregatorPair(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
+
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info("Client connected")
+            # Kick off the conversation.
+            messages.append(
+                {"role": "system", "content": "Please introduce yourself to the user."}
+            )
+            await task.queue_frames([LLMRunFrame()])
+
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info("Client disconnected")
+            await task.cancel()
+
+        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+        await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

pipecat_ai_typecast-0.0.1/pyproject.toml

@@ -0,0 +1,65 @@
+[project]
+name = "pipecat-ai-typecast"
+version = "0.0.1"
+description = "Typecast is an AI text-to-speech API that converts text into lifelike, expressive speech in many languages."
+license = "BSD-2-Clause"
+license-files = ["LICENSE"]
+readme = "README.md"
+requires-python = ">=3.10"
+keywords = ["pipecat", "text-to-speech", "ai"]
+authors = [
+    {name = "Neosapience", email = "help@typecast.ai"}
+]
+maintainers = [
+    {name = "Neosapience", email = "help@typecast.ai"}
+]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence"
+]
+dependencies = [
+    "pipecat-ai>=0.0.94",
+    "aiohttp>=3.9.0",
+    "loguru>=0.7.0",
+    "pydantic>=2.0.0",
+]
+
+[dependency-groups]
+dev = [
+    "pipecat-ai[daily,openai,deepgram,runner,webrtc,local-smart-turn-v3]>=0.0.94",
+    "python-dotenv>=1.0.1",
+    "onnxruntime>=1.23.2",
+    "ruff>=0.12.11",
+    "build>=1.0.0",
+    "twine>=5.0.0",
+]
+
+[project.urls]
+Homepage = "https://typecast.ai"
+Documentation = "https://typecast.ai/docs/overview"
+Source = "https://github.com/neosapience/pipecat-typecast"
+
+[build-system]
+requires = ["setuptools>=64", "setuptools_scm>=8"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.ruff]
+line-length = 100
+
+[tool.ruff.lint]
+select = [
+    "D", # Docstring rules
+    "I", # Import rules
+]
+
+[tool.ruff.lint.per-file-ignores]
+# Skip docstring checks for non-source code
+"example.py" = ["D"]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"

pipecat_ai_typecast-0.0.1/scripts/publish.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+# PyPI publish script
+# Usage: ./scripts/publish.sh [testpypi|pypi]
+
+set -e
+
+REPOSITORY=${1:-pypi}
+
+echo "Cleaning previous build artifacts..."
+rm -rf dist/ build/ *.egg-info
+
+echo "Building package..."
+python -m build
+
+echo "Build complete!"
+
+if [ "$REPOSITORY" = "testpypi" ]; then
+    echo "Uploading to TestPyPI..."
+    twine upload --repository testpypi dist/*
+    echo "TestPyPI publish complete!"
+    echo "Test installation: pip install --index-url https://test.pypi.org/simple/ pipecat-ai-typecast"
+else
+    echo "Uploading to PyPI..."
+    twine upload dist/*
+    echo "PyPI publish complete!"
+fi
+

pipecat_ai_typecast-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+