Docs /Templates/ sinapsis-openai

OpenAIAudioCreationWrapper

sinapsis-openaiOpenAI

Python template · sinapsis_openai.templates.openai_audio

Overview

Template that wraps the `OpenAI.audio.speech.create` API endpoint to perform audio creation tasks. This template excludes the `input` attribute (expected to be provided via the DataContainer packet `content`) and the `model` attribute (which is set in the template `AttributesBaseModel`) from the API caller. This ensures that the text input is dynamically extracted from the packet and that the speech model is passed exclusively via the template attributes. The PACKET_TYPE_NAME indicates that the template processes texts packets in the DataContainer

create — inherited documentation

Generates audio from the input text.

Returns the audio file content, or a stream of audio events.

Args: input: The text to generate audio for. The maximum length is 4096 characters.

model: One of the available [TTS models](https://platform.openai.com/docs/models#tts): `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, or `gpt-4o-mini-tts-2025-12-15`.

voice: The voice to use when generating the audio. Supported built-in voices are `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, `verse`, `marin`, and `cedar`. You may also provide a custom voice object with an `id`, for example `{ "id": "voice_1234" }`. Previews of the voices are available in the [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).

instructions: Control the voice of your generated audio with additional instructions. Does not work with `tts-1` or `tts-1-hd`.

response_format: The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`.

speed: The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is the default.

stream_format: The format to stream the audio in. Supported formats are `sse` and `audio`. `sse` is not supported for `tts-1` or `tts-1-hd`.

extra_headers: Send extra headers

extra_query: Add additional query parameters to the request

extra_body: Add additional JSON properties to the request

timeout: Override the client-level default timeout for this request, in seconds

Capabilities

Capabilities: not set

Installation

Install the published package using pip or uv.

Terminalbash
pip install sinapsis-openai==1.0.0
uv pip install sinapsis-openai==1.0.0
uv add sinapsis-openai==1.0.0

Configuration

Effective fields from the inspector schema, including nested Pydantic model fields.

modelRequired
Specifies the speech model to be used for generating audio. output_dir (str | None): Relative path where the binary audio output file will be saved (default is "openai/openai_audio.mp4"). openai_init api_key… Read full field description

Specifies the speech model to be used for generating audio. output_dir (str | None): Relative path where the binary audio output file will be saved (default is "openai/openai_audio.mp4"). openai_init api_key typing.Union[str, typing.Callable[[], str], NoneType]: default: None admin_api_key typing.Optional[str]: default: None workload_identity typing.Any: default: None organization typing.Optional[str]: default: None project typing.Optional[str]: default: None webhook_secret typing.Optional[str]: default: None provider typing.Any: default: None base_url typing.Any: default: None websocket_base_url typing.Any: default: None timeout typing.Any: default: NOT_GIVEN max_retries <class 'int'>: default: 2 default_headers typing.Optional[typing.Mapping[str, str]]: default: None default_query typing.Optional[typing.Mapping[str, object]]: default: None http_client typing.Any: default: None _strict_response_validation <class 'bool'>: default: False _enforce_credentials <class 'bool'>: default: Truecreate voice typing.Any: default: None instructions typing.Any: default: <openai.Omit object at 0x74f9db285a90> response_format typing.Any: default: <openai.Omit object at 0x74f9db285a90> speed typing.Any: default: <openai.Omit object at 0x74f9db285a90> stream_format typing.Any: default: <openai.Omit object at 0x74f9db285a90> extra_headers typing.Any: default: None extra_query typing.Any: default: None extra_body typing.Any: default: None timeout typing.Any: default: NOT_GIVEN

typing.Literal['tts-1', 'tts-1-hd', 'gpt-4o-mini-tts', 'gpt-4o-mini-tts-2025-12-15']
Required
Default: null
createRequired
createAttributes
Required
Default: null
speed
Any
Optional
Default: null
voice
Any
Optional
Default: null
timeout
Any
Optional
Default: null
extra_body
Any
Optional
Default: null
extra_query
Any
Optional
Default: null
instructions
Any
Optional
Default: null
extra_headers
Any
Optional
Default: null
stream_format
Any
Optional
Default: null
response_format
Any
Optional
Default: null
metadata
sinapsis_core.template_base.base_models.TemplateMetadata | None
Optional
Default: null
openai_initRequired
__init__Attributes
Required
Default: null
api_key
typing.Union[str, typing.Callable[[], str], NoneType]
Optional
Default: null
project
typing.Optional[str]
Optional
Default: null
timeout
Any
Optional
Default: null
base_url
Any
Optional
Default: null
provider
Any
Optional
Default: null
http_client
Any
Optional
Default: null
max_retries
int
Optional
Default: 2
organization
typing.Optional[str]
Optional
Default: null
admin_api_key
typing.Optional[str]
Optional
Default: null
default_query
typing.Optional[typing.Mapping[str, object]]
Optional
Default: null
webhook_secret
typing.Optional[str]
Optional
Default: null
default_headers
typing.Optional[typing.Mapping[str, str]]
Optional
Default: null
workload_identity
Any
Optional
Default: null
websocket_base_url
Any
Optional
Default: null

Configuration example

Example from the Python docstring:

yaml
agent:
  name: my_test_agent
templates:
- template_name: InputTemplate
  class_name: InputTemplate
- template_name: OpenAIAudioCreationWrapper
  class_name: OpenAIAudioCreationWrapper
  template_input: InputTemplate
  attributes:
    model: 'tts-1'
    output_dir: openai/openai_audio.mp4
    openai_init:
      api_key: openai_api_key
      max_retries: 2
    create:
      voice: 'alloy'
Show schema-based configuration skeleton
yaml
templates:
  - template_name: "OpenAIAudioCreationWrapper"
    class_name: "OpenAIAudioCreationWrapper"
    attributes:
      model: "<required>"
      create:
        speed: null
        voice: null
        timeout: null
        extra_body: null
        extra_query: null
        instructions: null
        extra_headers: null
        stream_format: null
        response_format: null
      openai_init:
        api_key: null
        project: null
        timeout: null
        base_url: null
        provider: null
        http_client: null
        max_retries: 2
        organization: null
        admin_api_key: null
        default_query: null
        webhook_secret: null
        default_headers: null
        workload_identity: null
        websocket_base_url: null

Inheritance

Immediate parent: sinapsis_openai.templates.openai_audio.OpenAIAudioCreation

Environment variables

Environment definitions belong to their canonical Python modules.

SINAPSIS_BUILD_DOCS · defined elsewhere