Annotate Speech with Timestamps

import audiostack
import os

audiostack.api_key = "YOUR_API_KEY"


scriptText = """
    <as:section name="intro" soundsegment="intro">
    In this example, you can see that it's possible to get a timestamp for every individual word that is produced.
    </as:section>

"""

script = audiostack.Content.Script.create(scriptText=scriptText, scriptName="test")

tts = audiostack.Speech.TTS.create(scriptItem=script, voice="joanna")

tts = audiostack.Speech.TTS.annotate(speechId=tts.speechId)

import audiostack
import os
import pandas as pd

audiostack.api_key = "YOUR_API_KEY"

scriptText = """
    <as:section name="intro" soundsegment="intro">
    In this example, you can see that it's possible to get a timestamp for every individual word that is produced.
    </as:section>

"""
print("Creating your script...")
script = audiostack.Content.Script.create(scriptText=scriptText, scriptName="test")

print("Generating speech...")
tts = audiostack.Speech.TTS.create(scriptItem=script, voice="joanna")
speechId = tts.speechId

print("Downloading your speech file...")
tts.download()

print("Annotating your speech file with time stamps...")
tts = audiostack.Speech.TTS.annotate(speechId=tts.speechId)

print("Formatting your timestamp data as a table...")
data_list = None
for key, value in tts['data'].items():
    if 'annotations_timestamps' in value:
        data_list = value['annotations_timestamps']
        break

df = pd.DataFrame(data_list)

df.rename(columns={'Offset': 'Timestamp'}, inplace=True)
df['Timestamp'] = df['Timestamp'] / 10000000
df['Duration'] = df['Duration'] / 10000000

# Print the formatted table
print(df)

import audiostack
import os
import pandas as pd

audiostack.api_key = "YOUR_API_KEY"

scriptText = """
    <as:section name="intro" soundsegment="intro">
    In this example, you can see that it's possible to get a timestamp for every individual word that is produced.
    </as:section>

"""
print("Creating your script...")
script = audiostack.Content.Script.create(scriptText=scriptText, scriptName="test")

print("Generating speech...")
tts = audiostack.Speech.TTS.create(scriptItem=script, voice="joanna")
speechId = tts.speechId

print("Downloading your speech file...")
tts.download()

print("Annotating your speech file with time stamps...")
tts = audiostack.Speech.TTS.annotate(speechId=tts.speechId)

print("Formatting your timestamp data as a table...")
data_list = None
for key, value in tts['data'].items():
    if 'annotations_timestamps' in value:
        data_list = value['annotations_timestamps']
        break

df = pd.DataFrame(data_list)

df.rename(columns={'Offset': 'Timestamp'}, inplace=True)
df['Timestamp'] = df['Timestamp'] / 10000000
df['Duration'] = df['Duration'] / 10000000

# Print the formatted table
print(df)

print("Generating a transcript...")
# Function to format the transcript for a given row
def format_transcript(row):
    start_time = row['Timestamp'].iloc[0]
    end_time = row['Timestamp'].iloc[-1] + row['Duration'].iloc[-1]
    words = ' '.join(row['Word'])
    return f"{start_time:.2f}-{end_time:.2f}\n\"{words}\""

# Group the data by continuous Timestamps and apply the format_transcript function
formatted_transcript = df.groupby((df['Timestamp'] != df['Timestamp'].shift(1) - df['Duration'].shift(1)).cumsum()).apply(format_transcript)

# Print the formatted transcript
print("Your Timestamped Transcript:")


# Initialize variables
segments = []
current_segment = pd.DataFrame(columns=['Word', 'Timestamp', 'Duration', 'Confidence'])

# Iterate through the data and create segments with at least 5 words
for _, row in df.iterrows():
    current_segment = pd.concat([current_segment, row.to_frame().T], ignore_index=True)
    words_in_segment = ' '.join(current_segment['Word']).split()
    if len(words_in_segment) >= 5: # This means that there are 5 words between each timestamp marker
        segments.append(current_segment)
        current_segment = pd.DataFrame(columns=['Word', 'Timestamp', 'Duration', 'Confidence'])

# If there are remaining words in the current segment, add it to the segments
if not current_segment.empty:
    segments.append(current_segment)

# Delete any existing content in the transcript file 
f = open("transcript.txt", "w")
f.close()
# Format and print the segments
for segment in segments:
    formatted_segment = format_transcript(segment)
    print(formatted_segment)
    f = open("transcript.txt", "a")
    print(f"{formatted_segment}", file=f)
    f.close()