Speech-to-Text

from audiopod import Client

client = Client()

# Simple YouTube transcription
transcription = client.transcription.transcribe_from_url(
    url="https://youtube.com/watch?v=example123",
    wait_for_completion=True  # Wait for result
)

print(f"Transcription completed!")
print(f"Duration: {transcription.duration}s")
print(f"Language: {transcription.language}")
print(f"Full text: {transcription.text}")

# Advanced transcription with speaker diarization
advanced_transcription = client.transcription.transcribe_from_url(
    url="https://youtube.com/watch?v=example123",
    language="en",  # Optional: auto-detect if not specified
    model_type="whisperx",  # whisperx, whisper_timestamped, faster_whisper
    enable_speaker_diarization=True,
    min_speakers=2,
    max_speakers=5,
    enable_word_timestamps=True,
    enable_confidence_scores=True,
    chunk_duration=1800,  # 30 minutes per chunk
    wait_for_completion=True
)

# Access speaker-separated text
for segment in advanced_transcription.segments:
    speaker = segment.get('speaker', 'Unknown')
    text = segment['text']
    start_time = segment['start']
    end_time = segment['end']
    confidence = segment.get('confidence', 0.0)
    
    print(f"[{start_time:.2f}s - {end_time:.2f}s] {speaker}: {text} (confidence: {confidence:.2f})")

# Batch processing multiple URLs
urls = [
    "https://youtube.com/watch?v=video1",
    "https://youtube.com/watch?v=video2",
    "https://vimeo.com/123456789"
]

batch_results = client.transcription.transcribe_batch_from_urls(
    urls=urls,
    enable_speaker_diarization=True,
    model_type="whisperx",
    wait_for_completion=True
)

for i, result in enumerate(batch_results):
    print(f"\nVideo {i+1}: {urls[i]}")
    print(f"Status: {result.status}")
    if result.status == "completed":
        print(f"Text preview: {result.text[:100]}...")

from audiopod import Client
import os

client = Client()

# Single file transcription
transcription = client.transcription.transcribe_from_file(
    audio_file="meeting_recording.mp3",
    language="en",
    model_type="whisperx",
    enable_speaker_diarization=True,
    min_speakers=2,
    max_speakers=8,
    enable_word_timestamps=True,
    enable_confidence_scores=True,
    wait_for_completion=True
)

print(f"Transcription completed!")
print(f"File: {transcription.source_file}")
print(f"Duration: {transcription.duration}s")
print(f"Language: {transcription.language}")
print(f"Full text: {transcription.text}")

# Access detailed segments with speakers
for segment in transcription.segments:
    speaker = segment.get('speaker', 'Unknown')
    text = segment['text']
    start_time = segment['start']
    end_time = segment['end']
    confidence = segment.get('confidence', 0.0)
    
    print(f"[{start_time:.2f}s - {end_time:.2f}s] {speaker}: {text}")

# Batch file transcription
audio_files = [
    "meeting_recording.mp3",
    "interview.wav", 
    "presentation.mp4",
    "podcast_episode.m4a"
]

batch_results = client.transcription.transcribe_batch_from_files(
    audio_files=audio_files,
    enable_speaker_diarization=True,
    model_type="whisperx",
    enable_word_timestamps=True,
    chunk_duration=1800,  # 30 minutes per chunk
    wait_for_completion=True
)

# Process results
for i, result in enumerate(batch_results):
    print(f"\nFile {i+1}: {audio_files[i]}")
    print(f"Status: {result.status}")
    if result.status == "completed":
        print(f"Duration: {result.duration}s")
        print(f"Language: {result.language}")
        print(f"Text preview: {result.text[:100]}...")
        
        # Save transcription to file
        output_file = f"transcript_{i+1}.txt"
        with open(output_file, 'w', encoding='utf-8') as f:
            f.write(result.text)
        print(f"Saved to: {output_file}")

# Advanced file processing with custom settings
def process_interview_file(file_path):
    """Process interview with optimized settings"""
    
    transcription = client.transcription.transcribe_from_file(
        audio_file=file_path,
        model_type="whisperx",  # Best for accuracy
        enable_speaker_diarization=True,
        min_speakers=2,  # Interviewer + interviewee
        max_speakers=4,  # Allow for additional participants
        enable_word_timestamps=True,
        enable_confidence_scores=True,
        language="auto",  # Auto-detect language
        wait_for_completion=True
    )
    
    # Generate formatted transcript
    formatted_output = []
    current_speaker = None
    
    for segment in transcription.segments:
        speaker = segment.get('speaker', 'Unknown')
        text = segment['text'].strip()
        
        if speaker != current_speaker:
            formatted_output.append(f"\n{speaker}:")
            current_speaker = speaker
            
        formatted_output.append(f" {text}")
    
    return ''.join(formatted_output)

# Process interview
interview_transcript = process_interview_file("important_interview.wav")
print("\nFormatted Interview Transcript:")
print(interview_transcript)

GET /api/v1/transcription/jobs/{job_id}
Authorization: Bearer {api_key}

GET /api/v1/transcription/jobs?status=COMPLETED&limit=50&offset=0
Authorization: Bearer {api_key}

GET /api/v1/transcription/jobs/{job_id}/transcript?format=json
Authorization: Bearer {api_key}

GET /api/v1/transcription/jobs/{job_id}/edit
Authorization: Bearer {api_key}

PUT /api/v1/transcription/jobs/{job_id}/edit
Authorization: Bearer {api_key}
Content-Type: application/json

{
  "segments": [
    {
      "id": 1,
      "start": 0.0,
      "end": 4.5,
      "text": "Welcome to our podcast about artificial intelligence.",
      "speaker_label": "SPEAKER_00",
      "confidence": 0.95
    }
  ],
  "edit_notes": "Corrected technical terms and speaker labels"
}

GET /api/v1/transcription/jobs/{job_id}/versions
Authorization: Bearer {api_key}

GET /api/v1/transcription/jobs/{job_id}/audio/{audio_index}
Authorization: Bearer {api_key}

DELETE /api/v1/transcription/jobs/{job_id}
Authorization: Bearer {api_key}