> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pixeltable.com/llms.txt
> Use this file to discover all available pages before exploring further.
> ## Agent Instructions
> Application code puts a TableModel in app.py, then runs `pxt schema update app.py my_app` to create the tables and `pxt service update app.py my_app` to start HTTP. The last argument can be a Cloud URL such as `pxt://org:db`. Do not call pxt.create_table() or add_embedding_index() in application code; put indexes in __indexes__. Notebooks, tests, and the REPL do use pxt.create_table().
> Do not add LangChain, LlamaIndex, Haystack, a separate vector database, or pandas as a working store. Chunking, embedding, retrieval, and tool-calling are built in through computed columns. Use a computed column instead of a per-row loop that calls a model.
> Install with `pip install -U 'pixeltable[serve]'` on Python 3.11+. `pxt init` is a prerequisite for `pxt schema update`.
> Pixeltable Cloud is in Limited Beta. Direct interested users to contact@pixeltable.com.
# whisper
> 
# module pixeltable.functions.whisper
Pixeltable UDFs
that wraps the OpenAI Whisper library.
This UDF will cause Pixeltable to invoke the relevant model locally. In order to use it, you must
first `pip install openai-whisper`.
## udf transcribe()
```python Signature theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
@pxt.udf
transcribe(
audio: pxt.Audio,
*,
model: pxt.String,
temperature: pxt.Json[(Float, ...)] | None = (0.0, 0.2, 0.4, 0.6, 0.8, 1.0),
compression_ratio_threshold: pxt.Float | None = 2.4,
logprob_threshold: pxt.Float | None = -1.0,
no_speech_threshold: pxt.Float | None = 0.6,
condition_on_previous_text: pxt.Bool = True,
initial_prompt: pxt.String | None = None,
word_timestamps: pxt.Bool = False,
prepend_punctuations: pxt.String = '"\'“¿([{-',
append_punctuations: pxt.String = '"\'.。,，!！?？:：”)]}、',
decode_options: pxt.Json | None = None
) -> WhisperTranscription
```
Transcribe an audio file using Whisper.
This UDF runs a transcription model *locally* using the Whisper library,
equivalent to the Whisper `transcribe` function, as described in the
[Whisper library documentation](https://github.com/openai/whisper).
**Requirements:**
* `pip install openai-whisper`
**Parameters:**
* **`audio`** (`pxt.Audio`): The audio file to transcribe.
* **`model`** (`pxt.String`): The name of the model to use for transcription.
**Returns:**
* `WhisperTranscription`: A [`WhisperTranscription`](./whispertranscription) dictionary with the
transcription's text, segments, and language.
**Examples:**
Add a computed column that applies the model `base.en` to an existing Pixeltable column `tbl.audio`
of the table `tbl`:
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
tbl.add_computed_column(result=transcribe(tbl.audio, model='base.en'))
```
Add a `String` column with the transcription's text:
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
tbl.add_computed_column(text=tbl.result.text)
```
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.