Python

pip install --upgrade typecast-python

from typecast import Typecast
from typecast.models import TTSRequest

# Initialize client
client = Typecast(api_key="YOUR_API_KEY")

# Convert text to speech
response = client.text_to_speech(TTSRequest(
    text="Hello there! I'm your friendly text-to-speech agent.",
    model="ssfm-v30",
    voice_id="tc_672c5f5ce59fac2a48faeaee"
))

# Save audio file
with open('output.wav', 'wb') as f:
    f.write(response.audio_data)

print(f"Duration: {response.duration}s, Format: {response.format}")

recommendations = client.recommend_voices(
    "warm female voice for a product tutorial",
    count=3,
)

for voice in recommendations:
    print(voice.voice_id, voice.voice_name, voice.score)

from typecast import Typecast
from typecast.models import TTSRequest, Output

client = Typecast()

response = client.text_to_speech(TTSRequest(
    text="Customized audio output!",
    model="ssfm-v30",
    voice_id="tc_672c5f5ce59fac2a48faeaee",
    output=Output(
        target_lufs=-14.0,   # Range: -70 to 0 (LUFS)
        audio_pitch=2,       # Range: -12 to +12 semitones
        audio_tempo=1.2,     # Range: 0.5x to 2.0x
        audio_format="mp3"   # Options: wav, mp3
    ),
    seed=42                  # Unsigned seed for reproducible results
))

client.generate_to_file(
    'output.mp3',
    text='Hello from Typecast.',
    voice_id='tc_672c5f5ce59fac2a48faeaee'  # Find voice IDs at https://studio.typecast.ai/developers/api/voices
)

# Async client
await async_client.generate_to_file(
    'output.mp3',
    text='Hello from Typecast.',
    voice_id='tc_672c5f5ce59fac2a48faeaee'  # Find voice IDs at https://studio.typecast.ai/developers/api/voices
)

response = (
    client.compose_speech()
    .defaults(voice_id="tc_672c5f5ce59fac2a48faeaee", model="ssfm-v30")
    .say("Hello<|5s|>Nice to meet you<|1s|>Today<|2s|>how does the weather feel?")
    .generate()
)

from typecast import Typecast
from typecast.models import Output

client = Typecast(api_key="YOUR_API_KEY")

response = (
    client.compose_speech()
    .defaults(voice_id="tc_672c5f5ce59fac2a48faeaee", model="ssfm-v30")
    .say("Hello there")
    .pause(5)
    .say("Nice to meet you", voice_id="tc_60e5426de8b95f1d3000d7b5", output=Output(audio_pitch=2))
    .say("Today")
    .pause(2)
    .say("How does the weather feel?")
    .generate()
)

with open("conversation.wav", "wb") as f:
    f.write(response.audio_data)

from typecast import Typecast
from typecast.models import VoicesV2Filter, TTSModel, GenderEnum, AgeEnum

client = Typecast()

# Get all voices
voices = client.voices_v2()

# Filter by criteria
filtered = client.voices_v2(VoicesV2Filter(
    model=TTSModel.SSFM_V30,
    gender=GenderEnum.FEMALE,
    age=AgeEnum.YOUNG_ADULT
))

# Display voice info
for voice in voices:
    print(f"ID: {voice.voice_id}, Name: {voice.voice_name}")
    print(f"Gender: {voice.gender}, Age: {voice.age}")
    print(f"Models: {', '.join(m.version.value for m in voice.models)}")
    print(f"Use cases: {voice.use_cases}")

import asyncio
from typecast import AsyncTypecast
from typecast.models import TTSRequest

async def main():
    async with AsyncTypecast() as client:
        response = await client.text_to_speech(TTSRequest(
            text="Hello from async!",
            model="ssfm-v30",
            voice_id="tc_672c5f5ce59fac2a48faeaee"
        ))

        with open('async_output.wav', 'wb') as f:
            f.write(response.audio_data)

asyncio.run(main())

# pip install requests sounddevice
import sounddevice as sd
from typecast import Typecast
from typecast.models import TTSRequestStream, OutputStream

client = Typecast()

request = TTSRequestStream(
    text="Stream this text as audio in real time.",
    model="ssfm-v30",
    voice_id="tc_672c5f5ce59fac2a48faeaee",
    output=OutputStream(audio_format="wav")
)

with sd.RawOutputStream(samplerate=32000, channels=1, dtype="int16") as player:
    buf, first = bytearray(), True
    for chunk in client.text_to_speech_stream(request):
        if first:
            chunk = chunk[44:]  # Skip 44-byte WAV header
            first = False
        buf.extend(chunk)
        n = len(buf) - (len(buf) % 2)  # int16 alignment
        if n:
            player.write(bytes(buf[:n]))
            del buf[:n]

from typecast import Typecast
from typecast.models import TTSRequestWithTimestamps

client = Typecast(api_key="YOUR_API_KEY")

response = client.text_to_speech_with_timestamps(TTSRequestWithTimestamps(
    text="Hello. How are you?",
    model="ssfm-v30",
    voice_id="tc_60e5426de8b95f1d3000d7b5",
))

# Save audio
with open("output.wav", "wb") as f:
    f.write(response.audio_bytes())

print(f"Duration: {response.audio_duration}s")
for word in response.words:
    print(f"  [{word.start_time:.3f}s – {word.end_time:.3f}s] {word.text}")

# Character-level alignment — required for Japanese / Chinese
response = client.text_to_speech_with_timestamps(TTSRequestWithTimestamps(
    text="Hello. How are you?",
    model="ssfm-v30",
    voice_id="tc_60e5426de8b95f1d3000d7b5",
    granularity="char",
))

for char in response.characters:
    print(f"  [{char.start_time:.3f}s – {char.end_time:.3f}s] {char.text}")

# Export SRT captions
srt_text = response.to_srt()
with open("output.srt", "w", encoding="utf-8") as f:
    f.write(srt_text)

# Export WebVTT captions
vtt_text = response.to_vtt()
with open("output.vtt", "w", encoding="utf-8") as f:
    f.write(vtt_text)

# Equivalent to writing audio_bytes() to a file
response.save_audio("output.wav")

from typecast import Typecast
from typecast.models import TTSRequest

client = Typecast(api_key="YOUR_API_KEY")

voice = client.clone_voice(
    audio="sample.wav",
    name="my-voice",
    model="ssfm-v30",
)

response = client.text_to_speech(TTSRequest(
    text="Hello from my cloned voice!",
    voice_id=voice.voice_id,
    model="ssfm-v30",
))

with open("output.wav", "wb") as f:
    f.write(response.audio_data)

client.delete_voice(voice.voice_id)

from typecast.models import TTSRequest, LanguageCode

response = client.text_to_speech(TTSRequest(
    text="Hello",
    model="ssfm-v30",
    voice_id="tc_672c5f5ce59fac2a48faeaee",
    language=LanguageCode.ENG
))

from typecast import (
    Typecast,
    TypecastError,
    BadRequestError,
    UnauthorizedError,
    PaymentRequiredError,
    NotFoundError,
    UnprocessableEntityError,
    RateLimitError,
    InternalServerError,
)

try:
    response = client.text_to_speech(request)
except UnauthorizedError:
    print("Invalid API key")
except PaymentRequiredError:
    print("Insufficient credits")
except RateLimitError:
    print("Rate limit exceeded - please retry later")
except TypecastError as e:
    print(f"Error {e.status_code}: {e.message}")