Transform audio to text and text to speech. Build voice-enabled applications with production-ready APIs.
"Hello, this is a demo of the MythicDot audio API..."
Convert audio recordings to accurate text transcriptions with automatic language detection.
Generate natural-sounding speech from text with multiple voice options and styles.
Translate audio from one language to English text in a single API call.
Analyze audio content directly with our multimodal models (coming soon).
Transcribe audio with high accuracy using our Whisper-based model:
from mythicdot import MythicDot
client = MythicDot()
# Transcribe audio file
with open("audio.mp3", "rb") as audio_file:
transcription = client.audio.transcriptions.create(
model="mythic-stt-1",
file=audio_file,
response_format="verbose_json", # Includes timestamps
timestamp_granularities=["word", "segment"]
)
print(transcription.text)
# Access word-level timestamps
for word in transcription.words:
print(f"{word.start:.2f}s: {word.word}")
Generate natural-sounding speech from text:
from mythicdot import MythicDot
client = MythicDot()
# Generate speech
response = client.audio.speech.create(
model="mythic-tts-1-hd",
voice="nova",
input="Welcome to MythicDot AI. Let's build something amazing together.",
response_format="mp3"
)
# Save to file
response.stream_to_file("output.mp3")
Neutral and balanced
Deep and authoritative
Warm and expressive
Deep and resonant
Friendly and conversational
Bright and clear
| Model | Description | Price |
|---|---|---|
| mythic-stt-1 | Speech-to-text transcription | $0.006 / minute |
| mythic-tts-1 | Standard text-to-speech | $0.015 / 1K chars |
| mythic-tts-1-hd | High-definition TTS | $0.030 / 1K chars |