Text Normalization

# With explicit language (recommended - fastest)
audio = client.tts.generate(
    text="I bought 3 items for €50.99 on 01/15/2024.",
    voice_id=1071,
    normalize=True,
    language="en",  # Specify language for best performance
)

# With auto-detection (may cause incorrect normalizations)
audio = client.tts.generate(
    text="Ich habe 3 Artikel für 50,99€ gekauft.",
    voice_id=1071,
    normalize=True,
    # language not specified - will auto-detect
)

# Spell out an email address
audio = client.tts.generate(
    text="Contact me at <spell>kajo@kugelaudio.com</spell>",
    voice_id=1071,
    normalize=True,
    language="en",
)
# Output: "Contact me at K, A, J, O, at, K, U, G, E, L, A, U, D, I, O, dot, C, O, M"

# Spell out an acronym
audio = client.tts.generate(
    text="The <spell>API</spell> is easy to use.",
    voice_id=1071,
    normalize=True,
    language="en",
)
# Output: "The A, P, I is easy to use."

# German example with language-specific translations
audio = client.tts.generate(
    text="Meine E-Mail ist <spell>test@beispiel.de</spell>",
    voice_id=1071,
    normalize=True,
    language="de",
)
# Output: "Meine E-Mail ist T, E, S, T, ät, B, E, I, S, P, I, E, L, Punkt, D, E"

# Streaming with spell tags - tags spanning chunks are handled automatically
async with client.tts.streaming_session(
    voice_id=1071,
    normalize=True,
    language="en",
) as session:
    # Even if the tag is split across tokens, it works correctly
    async for chunk in session.send("My code is <spell>"):
        play_audio(chunk.audio)
    async for chunk in session.send("ABC123</spell>"):
        play_audio(chunk.audio)
    async for chunk in session.flush():
        play_audio(chunk.audio)