AI_TRANSCRIBE

AI_TRANSCRIBE(
  file_reference,
  [options]
)

SELECT 
    file_name,
    AI_TRANSCRIBE(
        TO_FILE('@audio_stage/' || file_name)
    ) AS transcription
FROM DIRECTORY('@audio_stage')
WHERE file_name LIKE '%.mp3'

SELECT 
    AI_TRANSCRIBE(
        TO_FILE('@meetings/team_meeting_2024_01.mp4'),
        {'include_timestamps': true}
    ) AS

SELECT 
    meeting_id,
    AI_TRANSCRIBE(
        TO_FILE('@recordings/' || filename),
        {
            'identify_speakers': true,
            'include_timestamps': true
        }
    ) AS transcription
FROM meeting_recordings
WHERE meeting_date >= CURRENT_DATE - 7

SELECT 
    AI_TRANSCRIBE(
        TO_FILE('@podcasts/episode_45.mp3'),
        {'language': 'es'}  -- Spanish
    ) AS

CREATE TABLE call_transcriptions AS
SELECT 
    call_id,
    customer_id,
    call_date,
    AI_TRANSCRIBE(
        TO_FILE('@call_recordings/' || recording_file),
        {'identify_speakers': true}
    ) AS transcription,
    CURRENT_TIMESTAMP() AS transcribed_at
FROM customer_calls
WHERE transcribed_at IS NULL
  AND call_date >= CURRENT_DATE - 30

CREATE STAGE audio_transcriptions
  DIRECTORY = (ENABLE = true)
  ENCRYPTION = (TYPE = 'SNOWFLAKE_SSE');

PUT file://local_audio/*.mp3 @audio_transcriptions AUTO_COMPRESS = FALSE;

CREATE TABLE meeting_transcripts (
    meeting_id VARCHAR,
    recording_file VARCHAR,
    transcription VARIANT,
    transcription_date TIMESTAMP DEFAULT CURRENT_TIMESTAMP()
);

INSERT INTO meeting_transcripts
SELECT 
    meeting_id,
    filename,
    AI_TRANSCRIBE(TO_FILE('@meetings/' || filename))
FROM

-- Extract text from transcription
SELECT 
    meeting_id,
    transcription:text::STRING AS full_text,
    transcription:duration::FLOAT AS duration_seconds
FROM meeting_transcripts;

-- Analyze with other AI functions
SELECT 
    meeting_id,
    AI_SENTIMENT(transcription:text::STRING) AS meeting_sentiment,
    AI_EXTRACT(
        transcription:text::STRING,
        'Extract action items and decisions made'
    ) AS key_outcomes
FROM

-- Process recordings in manageable batches
CREATE OR REPLACE TASK transcribe_daily_recordings
  WAREHOUSE = compute_wh
  SCHEDULE = 'USING CRON 0 2 * * * UTC'  -- 2 AM daily
AS
  INSERT INTO transcriptions
  SELECT 
      file_url,
      AI_TRANSCRIBE(TO_FILE(file_url))
  FROM pending_transcriptions
  LIMIT 100;  -- Process 100 at a time

SELECT 
    meeting_id,
    meeting_title,
    AI_COMPLETE(
        'claude-4-sonnet',
        'Create meeting minutes from this transcript: ' || transcription:text::STRING
    ) AS meeting_minutes
FROM meeting_transcripts
WHERE meeting_date >= CURRENT_DATE - 7

SELECT 
    agent_id,
    COUNT(*) AS calls_analyzed,
    AVG(AI_SENTIMENT(transcription:text::STRING)) AS avg_sentiment,
    AI_AGG(
        transcription:text::STRING,
        'Identify common customer complaints'
    ) AS common_issues
FROM call_transcriptions
GROUP BY

SELECT 
    call_id,
    AI_FILTER(
        'Does this call mention required compliance disclosures?',
        transcription:text::STRING
    ) AS compliance_check
FROM call_transcriptions
WHERE compliance_check = false