# This file was auto-generated by Fern from our API Definition. import contextlib import typing from json.decoder import JSONDecodeError from ..core.api_error import ApiError from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper from ..core.http_response import AsyncHttpResponse, HttpResponse from ..core.request_options import RequestOptions from ..core.unchecked_base_model import construct_type from ..errors.unprocessable_entity_error import UnprocessableEntityError from ..types.http_validation_error import HttpValidationError from .types.text_to_sound_effects_convert_request_output_format import TextToSoundEffectsConvertRequestOutputFormat # this is used as the default value for optional parameters OMIT = typing.cast(typing.Any, ...) class RawTextToSoundEffectsClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._client_wrapper = client_wrapper @contextlib.contextmanager def convert( self, *, text: str, output_format: typing.Optional[TextToSoundEffectsConvertRequestOutputFormat] = None, loop: typing.Optional[bool] = OMIT, duration_seconds: typing.Optional[float] = OMIT, prompt_influence: typing.Optional[float] = OMIT, model_id: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> typing.Iterator[HttpResponse[typing.Iterator[bytes]]]: """ Turn text into sound effects for your videos, voice-overs or video games using the most advanced sound effects models in the world. Parameters ---------- text : str The text that will get converted into a sound effect. output_format : typing.Optional[TextToSoundEffectsConvertRequestOutputFormat] Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. loop : typing.Optional[bool] Whether to create a sound effect that loops smoothly. Only available for the 'eleven_text_to_sound_v2 model'. duration_seconds : typing.Optional[float] The duration of the sound which will be generated in seconds. Must be at least 0.5 and at most 30. If set to None we will guess the optimal duration using the prompt. Defaults to None. prompt_influence : typing.Optional[float] A higher prompt influence makes your generation follow the prompt more closely while also making generations less variable. Must be a value between 0 and 1. Defaults to 0.3. model_id : typing.Optional[str] The model ID to use for the sound generation. request_options : typing.Optional[RequestOptions] Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response. Returns ------- typing.Iterator[HttpResponse[typing.Iterator[bytes]]] The generated sound effect as an MP3 file """ with self._client_wrapper.httpx_client.stream( "v1/sound-generation", method="POST", params={ "output_format": output_format, }, json={ "text": text, "loop": loop, "duration_seconds": duration_seconds, "prompt_influence": prompt_influence, "model_id": model_id, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) as _response: def _stream() -> HttpResponse[typing.Iterator[bytes]]: try: if 200 <= _response.status_code < 300: _chunk_size = request_options.get("chunk_size", 1024) if request_options is not None else 1024 return HttpResponse( response=_response, data=(_chunk for _chunk in _response.iter_bytes(chunk_size=_chunk_size)) ) _response.read() if _response.status_code == 422: raise UnprocessableEntityError( headers=dict(_response.headers), body=typing.cast( HttpValidationError, construct_type( type_=HttpValidationError, # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError( status_code=_response.status_code, headers=dict(_response.headers), body=_response.text ) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) yield _stream() class AsyncRawTextToSoundEffectsClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._client_wrapper = client_wrapper @contextlib.asynccontextmanager async def convert( self, *, text: str, output_format: typing.Optional[TextToSoundEffectsConvertRequestOutputFormat] = None, loop: typing.Optional[bool] = OMIT, duration_seconds: typing.Optional[float] = OMIT, prompt_influence: typing.Optional[float] = OMIT, model_id: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[bytes]]]: """ Turn text into sound effects for your videos, voice-overs or video games using the most advanced sound effects models in the world. Parameters ---------- text : str The text that will get converted into a sound effect. output_format : typing.Optional[TextToSoundEffectsConvertRequestOutputFormat] Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. loop : typing.Optional[bool] Whether to create a sound effect that loops smoothly. Only available for the 'eleven_text_to_sound_v2 model'. duration_seconds : typing.Optional[float] The duration of the sound which will be generated in seconds. Must be at least 0.5 and at most 30. If set to None we will guess the optimal duration using the prompt. Defaults to None. prompt_influence : typing.Optional[float] A higher prompt influence makes your generation follow the prompt more closely while also making generations less variable. Must be a value between 0 and 1. Defaults to 0.3. model_id : typing.Optional[str] The model ID to use for the sound generation. request_options : typing.Optional[RequestOptions] Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response. Returns ------- typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[bytes]]] The generated sound effect as an MP3 file """ async with self._client_wrapper.httpx_client.stream( "v1/sound-generation", method="POST", params={ "output_format": output_format, }, json={ "text": text, "loop": loop, "duration_seconds": duration_seconds, "prompt_influence": prompt_influence, "model_id": model_id, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) as _response: async def _stream() -> AsyncHttpResponse[typing.AsyncIterator[bytes]]: try: if 200 <= _response.status_code < 300: _chunk_size = request_options.get("chunk_size", 1024) if request_options is not None else 1024 return AsyncHttpResponse( response=_response, data=(_chunk async for _chunk in _response.aiter_bytes(chunk_size=_chunk_size)), ) await _response.aread() if _response.status_code == 422: raise UnprocessableEntityError( headers=dict(_response.headers), body=typing.cast( HttpValidationError, construct_type( type_=HttpValidationError, # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError( status_code=_response.status_code, headers=dict(_response.headers), body=_response.text ) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) yield await _stream()