Voice Synthesis

def tts(
    text: str,
    voice: str = "none",
    filename: str = "output.mp3",
    play_sound: bool = False,
) -> None:
    """
    Creates a text-to-speech audio file using TikTok's voice API.
    
    Args:
        text (str): The text to convert to speech.
        voice (str): The voice ID to use.
        filename (str): Output audio file path.
        play_sound (bool): Whether to play the audio after generation.
    """

"en_us_ghostface"    # Ghost Face
"en_us_chewbacca"    # Chewbacca
"en_us_c3po"         # C3PO
"en_us_stitch"       # Stitch
"en_us_stormtrooper" # Stormtrooper
"en_us_rocket"       # Rocket

"en_au_001"  # English AU - Female
"en_au_002"  # English AU - Male
"en_uk_001"  # English UK - Male 1
"en_uk_003"  # English UK - Male 2
"en_us_001"  # English US - Female (Int. 1)
"en_us_002"  # English US - Female (Int. 2)
"en_us_006"  # English US - Male 1
"en_us_007"  # English US - Male 2
"en_us_009"  # English US - Male 3
"en_us_010"  # English US - Male 4

"fr_001"  # French - Male 1
"fr_002"  # French - Male 2
"de_001"  # German - Female
"de_002"  # German - Male
"es_002"  # Spanish - Male

"es_mx_002"  # Spanish MX - Male
"br_001"     # Portuguese BR - Female 1
"br_003"     # Portuguese BR - Female 2
"br_004"     # Portuguese BR - Female 3
"br_005"     # Portuguese BR - Male

"id_001"  # Indonesian - Female
"jp_001"  # Japanese - Female 1
"jp_003"  # Japanese - Female 2
"jp_005"  # Japanese - Female 3
"jp_006"  # Japanese - Male
"kr_002"  # Korean - Male 1
"kr_003"  # Korean - Female
"kr_004"  # Korean - Male 2

"en_female_f08_salut_damour"  # Alto
"en_male_m03_lobby"            # Tenor
"en_female_f08_warmy_breeze"   # Warmy Breeze
"en_male_m03_sunshine_soon"    # Sunshine Soon

"en_male_narration"      # Narrator
"en_male_funny"          # Wacky
"en_female_emotional"    # Peaceful

ENDPOINTS = [
    "https://tiktok-tts.weilnet.workers.dev/api/generation",
    "https://tiktoktts.com/api/tiktok-tts",
]

TEXT_BYTE_LIMIT = 300

def split_string(string: str, chunk_size: int) -> List[str]:
    """Split a string into chunks of maximum chunk_size, 
    breaking at word boundaries."""
    words = string.split()
    result = []
    current_chunk = ""
    for word in words:
        if len(current_chunk) + len(word) + 1 <= chunk_size:
            current_chunk += f" {word}"
        else:
            if current_chunk:
                result.append(current_chunk.strip())
            current_chunk = word
    if current_chunk:
        result.append(current_chunk.strip())
    return result

# Split longer text into smaller parts
text_parts = split_string(text, 299)
audio_base64_data = [None] * len(text_parts)

# Define a thread function to generate audio for each text part
def generate_audio_thread(text_part, index):
    audio = generate_audio(text_part, voice)
    # Parse base64 from response
    audio_base64_data[index] = base64_data

threads = []
for index, text_part in enumerate(text_parts):
    thread = threading.Thread(
        target=generate_audio_thread, args=(text_part, index)
    )
    thread.start()
    threads.append(thread)

# Wait for all threads to complete
for thread in threads:
    thread.join()

# Concatenate the base64 data in the correct order
audio_base64_data = "".join(audio_base64_data)

def generate_audio(text: str, voice: str) -> bytes:
    """Send POST request to get the audio data."""
    url = f"{ENDPOINTS[current_endpoint]}"
    headers = {"Content-Type": "application/json"}
    data = {"text": text, "voice": voice}
    response = requests.post(url, headers=headers, json=data)
    return response.content

{
  "data": "data:audio/mpeg;base64,SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2Z..."
}

if current_endpoint == 0:
    audio_base64_data = str(audio).split('"')[5]
else:
    audio_base64_data = str(audio).split('"')[3].split(",")[1]

def save_audio_file(base64_data: str, filename: str = "output.mp3") -> None:
    """Save base64-encoded audio to an MP3 file."""
    audio_bytes = base64.b64decode(base64_data)
    with open(filename, "wb") as file:
        file.write(audio_bytes)

from Backend.tiktokvoice import tts, VOICES

# Generate TTS audio
tts(
    text="Welcome to this video about space exploration. Today we'll learn about the Mars rover mission.",
    voice="en_us_001",
    filename="voiceover.mp3",
    play_sound=False
)

print("Audio generated: voiceover.mp3")

# List all available voices
print(f"Available voices: {len(VOICES)}")
for voice in VOICES:
    print(f"  - {voice}")

# Check service availability
if get_api_response().status_code == 200:
    log("[+] TikTok TTS Service available!", "success")
else:
    # Try fallback endpoint
    current_endpoint = (current_endpoint + 1) % 2
    if get_api_response().status_code == 200:
        log("[+] TTS Service available!", "success")
    else:
        log("[-] TTS Service not available and probably temporarily rate limited", "error")
        return

# Validate voice
if voice not in VOICES:
    log("[-] Voice not available", "error")
    return

# Validate text
if not text:
    log("[-] Please specify a text", "error")
    return

def get_api_response() -> requests.Response:
    """Check if the TTS service is available."""
    url = f'{ENDPOINTS[current_endpoint].split("/a")[0]}'
    response = requests.get(url)
    return response