LlamaIndex

pip install llama-index-tools-typecast

from llama_index.tools.typecast import TypecastToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Initialize the Typecast tool
speech_tool = TypecastToolSpec(api_key="your-typecast-key")

# Create an agent with Typecast capabilities
agent = FunctionAgent(
    tools=speech_tool.to_tool_list(),
    llm=OpenAI(model="gpt-4o-mini"),
)

# Generate speech through the agent
result = await agent.run(
    'Create speech from the text "Hello world!" with a happy emotion '
    'and output the file to "speech.wav"'
)
print(result)

from llama_index.tools.typecast import TypecastToolSpec

speech_tool = TypecastToolSpec(api_key="your-typecast-key")

# Get all available voices with optional filters
voices = speech_tool.get_voices(
    model="ssfm-v30",
    gender="female",
    age="young_adult",
    use_case="Audiobook"
)
print(f"Found {len(voices)} voices")

for voice in voices:
    print(f"{voice['voice_name']} ({voice['voice_id']})")

# Get specific voice information
voice = speech_tool.get_voice("tc_62a8975e695ad26f7fb514d1")
print(f"Voice: {voice['voice_name']}")
print(f"Gender: {voice.get('gender')}, Age: {voice.get('age')}")
print(f"Use cases: {voice.get('use_cases')}")

# Models include supported emotions
for model in voice["models"]:
    print(f"Model {model['version']}: emotions = {model['emotions']}")

# Text-to-speech with full parameter control
output_path = speech_tool.text_to_speech(
    text="Hello world! This is a test.",
    voice_id="tc_62a8975e695ad26f7fb514d1",
    output_path="speech.wav",
    model="ssfm-v30",
    language="eng",
    emotion_preset="happy",
    emotion_intensity=1.5,
    volume=100,
    audio_pitch=0,
    audio_tempo=1.0,
    audio_format="wav",
    seed=42,  # Unsigned seed for reproducible results
)
print(f"Audio saved to: {output_path}")

import os
from llama_index.tools.typecast import TypecastToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Set up API keys
os.environ["OPENAI_API_KEY"] = "your-openai-key"

# Initialize Typecast tool
speech_tool = TypecastToolSpec(api_key="your-typecast-key")

# Create agent with Typecast capabilities
agent = FunctionAgent(
    tools=speech_tool.to_tool_list(),
    llm=OpenAI(model="gpt-4o-mini"),
)

# Let the agent discover voices and generate speech
result = await agent.run(
    'Get the list of available voices, select the first female voice, '
    'and use it to create speech from the text "Welcome to Typecast!" '
    'with a happy emotion, saving to "welcome.wav"'
)
print(result)