Speech to Text API - Whisper & More

from openai import OpenAI

# Initialize VoltageGPU client
client = OpenAI(
    base_url="https://api.voltagegpu.com/v1",
    api_key="YOUR_VOLTAGE_API_KEY"
)

# Transcribe an audio file
with open("interview.mp3", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-large-v3",
        file=audio_file,
        response_format="verbose_json",
        timestamp_granularities=["word"],
    )

print(f"Transcription: {transcript.text}")
print(f"Language: {transcript.language}")
print(f"Duration: {transcript.duration}s")

# Access word-level timestamps
for word in transcript.words:
    print(f"  [{word.start:.2f}s - {word.end:.2f}s] {word.word}")

# Translation (any language to English)
with open("french_podcast.mp3", "rb") as audio_file:
    translation = client.audio.translations.create(
        model="whisper-large-v3",
        file=audio_file,
    )

print(f"English translation: {translation.text}")