Speech-to-Text

curl https://aihubmix.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $AIHUBMIX_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@/path/to/file/audio.mp3" \
  -F model="whisper-large-v3" \
  -F response_format="text" \
  -F temperature="0.2"

curl https://aihubmix.com/v1/audio/translations \
  -H "Authorization: Bearer $AIHUBMIX_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@/path/to/file/audio.mp3" \
  -F model="whisper-large-v3" \
  -F prompt="autocorrect, clean up the stammer, and translate to english" \
  -F response_format="text" \
  -F temperature="0.2"

from openai import OpenAI
import os

client = OpenAI(
  api_key="sk-***", # Replace with your AiHubMix API key
  base_url="https://aihubmix.com/v1"
)

# Open audio file
audio_file = open("path/to/audio.mp3", "rb")

# Transcribe audio
transcript = client.audio.transcriptions.create(
  model="whisper-large-v3",
  file=audio_file,
  language="en",  # Specify English for better accuracy
  prompt="Please transcribe accurately with proper punctuation and grammar",
  response_format="text",
  temperature=0.2  # Lower randomness to reduce hallucinations
)

print(transcript)

from openai import OpenAI
import os

client = OpenAI(
  api_key="sk-***", # Replace with your AiHubMix API key
  base_url="https://aihubmix.com/v1"
)

# Open audio file
audio_file = open("path/to/audio.m4a", "rb")

# Translate audio to English
translation = client.audio.translations.create(
  model="whisper-large-v3",
  file=audio_file,
  prompt="autocorrect, clean up the stammer, and translate to english",
  response_format="text",
  temperature=0.2
)

print(translation)

from openai import OpenAI
import os

client = OpenAI(
  api_key="sk-***", # Replace with your AiHubMix API key
  base_url="https://aihubmix.com/v1"
)

audio_file = open("path/to/audio.wav", "rb")

# Get detailed transcription results with timestamps
transcript = client.audio.transcriptions.create(
  model="whisper-large-v3",
  file=audio_file,
  response_format="verbose_json",
  timestamp_granularities=["word"],
  temperature=0.2
)

# Output results with word-level timestamps
print(f"Text: {transcript.text}")
print(f"Language: {transcript.language}")
for word in transcript.words:
    print(f"'{word.word}' at {word.start}s - {word.end}s")

from openai import OpenAI
import os

client = OpenAI(
  api_key="sk-***", # Replace with your AiHubMix API key
  base_url="https://aihubmix.com/v1"
)

audio_file = open("path/to/video_audio.mp4", "rb")

# Generate SRT subtitle file
srt_transcript = client.audio.transcriptions.create(
  model="whisper-large-v3",
  file=audio_file,
  response_format="srt",
  language="en",
  temperature=0.2
)

# Save as .srt file
with open("subtitles.srt", "w", encoding="utf-8") as f:
    f.write(srt_transcript)

print("SRT subtitle file generated")