Transcribe Recordings

The Pipe Platform now directly integrates with Replicate to provide audio transcription using a very fast variant of OpenAI’s Whisper model Large V3. The transcription is done as part of the processing pipeline, and the transcription will be available as a separate JSON file.

Note: the transcription feature in a BETA feature as we are finetuning the implementation, evaluating associated costs and other models.

Turning Transcription ON #

Enabling it is very easy:

1. Go to the Transcoding section in the Pipe Account Dashboard.
2. Scroll to the Audio Transcription section and toogle on Transcribe new recordings.
3. Save.

The recording audio will be sent to the Replicate servers for transcription. Audio extraction does not need to be enabled for this to work, but if enabled, it will provide the audio data for transcription. Transcription generally takes a few seconds to a few minutes depending on the length of the recording.

Supported Languages #

The current model supports 100 languages: afrikaans, albanian, amharic, arabic, armenian, assamese, azerbaijani, bashkir, basque, belarusian, bengali, bosnian, breton, bulgarian, cantonese, catalan, chinese, croatian, czech, danish, dutch, english, estonian, faroese, finnish, french, galician, georgian, german, greek, gujarati, haitian creole, hausa, hawaiian, hebrew, hindi, hungarian, icelandic, indonesian, italian, japanese, javanese, kannada, kazakh, khmer, korean, lao, latin, latvian, lingala, lithuanian, luxembourgish, macedonian, malagasy, malay, malayalam, maltese, maori, marathi, mongolian, myanmar, nepali, norwegian, nynorsk, occitan, pashto, persian, polish, portuguese, punjabi, romanian, russian, sanskrit, serbian, shona, sindhi, sinhala, slovak, slovenian, somali, spanish, sundanese, swahili, swedish, tagalog, tajik, tamil, tatar, telugu, thai, tibetan, turkish, turkmen, ukrainian, urdu, uzbek, vietnamese, welsh, yiddish, yoruba.

The language is automatically detected.

Output #

The resulting transcription file will be pushed to Pipe’s complimentary storage (if enabled) and to your own storage (if configured), together with all the other files related to a recording.

The filename will be STREAMNAME_transcript.json.

The JSON file contains an object with metadata about the transcription job and an output object with the transcription results.

output.chunks contains the transcript split into timestamped segments. Each segment includes:

• text — the transcribed text for that segment, including punctuation.
• timestamp — a two-element array containing the segment’s start and end times in seconds.

output.text contains the complete transcription as a single string.

The top-level object also includes metadata such as the schema version, recording ID and name, transcription provider and model, prediction ID, and completion timestamp.

Here’s an example with the contents of such a JSON transcription file:

{
    "schema_version": 1,
    "recording_id": 123,
    "recording_name": "STREAM_NAME",
    "provider": "replicate",
    "model": "vaibhavs10/incredibly-fast-whisper",
    "version": "model_version_hash",
    "prediction_id": "prediction_id",
    "completed_at": "2026-09-02T08:22:00Z",
    "output": {
        "chunks": [
          {
            "text": " The little tales they tell are false the door was barred locked and bolted as well ripe pears are fit hours fly by much too soon. The room was crowded",
            "timestamp": [
              0,
              29.72
            ]
          },
          {
            "text": " with a mild wab. The room was crowded with a wild mob. This strong arm shall shield your",
            "timestamp": [
              29.72,
              38.98
            ]
          },
          {
            "text": " honour. She blushed when he gave her a white orchid The beetle droned in the hot June sun",
            "timestamp": [
              38.98,
              48.52
            ]
          }
        ],
        "text": " The little tales they tell are false the door was barred locked and bolted as well ripe pears are fit hours fly by much too soon. The room was crowded with a mild wab. The room was crowded with a wild mob. This strong arm shall shield your honour. She blushed when he gave her a white orchid The beetle droned in the hot June sun"
    }
}

Data Retention #

The audio data will be kept by Replicate while the transcription runs and will be deleted immediately after the transcription is completed. The transcription data will remain on the Replicate servers for up to 1 hour after transcription is completed.