# This file was auto-generated by Fern from our API Definition. import typing from ....core.client_wrapper import AsyncClientWrapper, SyncClientWrapper from ....core.request_options import RequestOptions from .raw_client import AsyncRawAudioClient, RawAudioClient from .types.audio_generate_request_callback_method import AudioGenerateRequestCallbackMethod from .types.audio_generate_request_container import AudioGenerateRequestContainer from .types.audio_generate_request_encoding import AudioGenerateRequestEncoding # this is used as the default value for optional parameters OMIT = typing.cast(typing.Any, ...) class AudioClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._raw_client = RawAudioClient(client_wrapper=client_wrapper) @property def with_raw_response(self) -> RawAudioClient: """ Retrieves a raw implementation of this client that returns raw responses. Returns ------- RawAudioClient """ return self._raw_client def generate( self, *, model: str, text: str, callback: typing.Optional[str] = None, callback_method: typing.Optional[AudioGenerateRequestCallbackMethod] = None, mip_opt_out: typing.Optional[bool] = None, tag: typing.Optional[typing.Union[str, typing.Sequence[str]]] = None, bit_rate: typing.Optional[int] = None, container: typing.Optional[AudioGenerateRequestContainer] = None, encoding: typing.Optional[AudioGenerateRequestEncoding] = None, expressivity: typing.Optional[int] = None, sample_rate: typing.Optional[int] = None, speed: typing.Optional[float] = None, priority: typing.Optional[typing.Literal["low"]] = None, request_options: typing.Optional[RequestOptions] = None, ) -> typing.Iterator[bytes]: """ Synthesize a complete block of text into a single audio response using Deepgram's Flux TTS batch (REST) API. Use this for pre-rendering fixed audio (IVR prompts, notifications, narration) where the whole text is known up front and you don't need incremental playback or interruption. Parameters ---------- model : str Flux TTS model used to synthesize the submitted text, in the form `flux-{voice}-{language}` (for example, `flux-alexis-en`). Required; unlike the v1 (Aura) endpoint there is no default and only flux models are accepted. English-only at launch. text : str The text content to be converted to speech. The server normalizes and preprocesses the text before synthesis. Inline pause and pronunciation controls are not yet applied; they are stripped from the text before synthesis. callback : typing.Optional[str] URL to which we'll make the callback request callback_method : typing.Optional[AudioGenerateRequestCallbackMethod] HTTP method by which the callback request will be made mip_opt_out : typing.Optional[bool] Opts out requests from the Deepgram Model Improvement Program. Refer to our Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip tag : typing.Optional[typing.Union[str, typing.Sequence[str]]] Label your requests for the purpose of identification during usage reporting bit_rate : typing.Optional[int] The bitrate of the audio in bits per second. Choose from predefined ranges or specific values based on the encoding type. container : typing.Optional[AudioGenerateRequestContainer] Container specifies the file format wrapper for the output audio. The available options depend on the encoding type. encoding : typing.Optional[AudioGenerateRequestEncoding] Encoding allows you to specify the expected encoding of your audio output expressivity : typing.Optional[int] Expressive range of the generated speech, on a calm-to-animated axis. Accepted values: `-2`, `-1`, `0`, `1`, `2`. `0` (the default) is the voice's tuned delivery and the production-validated setting, with `-2` the calm end of the range and `2` the animated end. Supported on all Flux voices; applies to the whole request. Beta: behavior may change in future model versions, and non-default values increase the risk of hallucinations and pronunciation errors; audition before shipping. An invalid value is rejected with a `400` — `EXPRESSIVITY_OUT_OF_RANGE` for a value outside the range, `EXPRESSIVITY_INCREMENT_INVALID` for a fractional value. See [Expressivity](/docs/tts-expressivity). sample_rate : typing.Optional[int] Sample Rate specifies the sample rate for the output audio. Based on the encoding, different sample rates are supported. For some encodings, the sample rate is not configurable speed : typing.Optional[float] Speaking rate multiplier that adjusts the pace of generated speech while preserving natural prosody and voice quality. Accepted values run `0.85` to `1.15` in `0.05` increments. Not yet supported in all languages. priority : typing.Optional[typing.Literal["low"]] Processing priority for asynchronous (callback) requests. The only supported value is low. 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[bytes] Returns the synthesized audio in the requested encoding as a binary stream. When a `callback` URL is supplied, the request is processed asynchronously and the response body is instead a JSON acknowledgement (Content-Type `application/json`) of the form {"request_id": "..."}, with the audio delivered to the callback URL. Because this endpoint is typed as a binary audio stream, SDK callers that set `callback` receive this JSON acknowledgement through the audio byte iterator as raw bytes and must join the chunks and parse `request_id` themselves. Examples -------- from deepgram import DeepgramClient client = DeepgramClient( api_key="YOUR_API_KEY", ) client.speak.v2.audio.generate( model="model", text="text", ) """ with self._raw_client.generate( model=model, text=text, callback=callback, callback_method=callback_method, mip_opt_out=mip_opt_out, tag=tag, bit_rate=bit_rate, container=container, encoding=encoding, expressivity=expressivity, sample_rate=sample_rate, speed=speed, priority=priority, request_options=request_options, ) as r: yield from r.data class AsyncAudioClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._raw_client = AsyncRawAudioClient(client_wrapper=client_wrapper) @property def with_raw_response(self) -> AsyncRawAudioClient: """ Retrieves a raw implementation of this client that returns raw responses. Returns ------- AsyncRawAudioClient """ return self._raw_client async def generate( self, *, model: str, text: str, callback: typing.Optional[str] = None, callback_method: typing.Optional[AudioGenerateRequestCallbackMethod] = None, mip_opt_out: typing.Optional[bool] = None, tag: typing.Optional[typing.Union[str, typing.Sequence[str]]] = None, bit_rate: typing.Optional[int] = None, container: typing.Optional[AudioGenerateRequestContainer] = None, encoding: typing.Optional[AudioGenerateRequestEncoding] = None, expressivity: typing.Optional[int] = None, sample_rate: typing.Optional[int] = None, speed: typing.Optional[float] = None, priority: typing.Optional[typing.Literal["low"]] = None, request_options: typing.Optional[RequestOptions] = None, ) -> typing.AsyncIterator[bytes]: """ Synthesize a complete block of text into a single audio response using Deepgram's Flux TTS batch (REST) API. Use this for pre-rendering fixed audio (IVR prompts, notifications, narration) where the whole text is known up front and you don't need incremental playback or interruption. Parameters ---------- model : str Flux TTS model used to synthesize the submitted text, in the form `flux-{voice}-{language}` (for example, `flux-alexis-en`). Required; unlike the v1 (Aura) endpoint there is no default and only flux models are accepted. English-only at launch. text : str The text content to be converted to speech. The server normalizes and preprocesses the text before synthesis. Inline pause and pronunciation controls are not yet applied; they are stripped from the text before synthesis. callback : typing.Optional[str] URL to which we'll make the callback request callback_method : typing.Optional[AudioGenerateRequestCallbackMethod] HTTP method by which the callback request will be made mip_opt_out : typing.Optional[bool] Opts out requests from the Deepgram Model Improvement Program. Refer to our Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip tag : typing.Optional[typing.Union[str, typing.Sequence[str]]] Label your requests for the purpose of identification during usage reporting bit_rate : typing.Optional[int] The bitrate of the audio in bits per second. Choose from predefined ranges or specific values based on the encoding type. container : typing.Optional[AudioGenerateRequestContainer] Container specifies the file format wrapper for the output audio. The available options depend on the encoding type. encoding : typing.Optional[AudioGenerateRequestEncoding] Encoding allows you to specify the expected encoding of your audio output expressivity : typing.Optional[int] Expressive range of the generated speech, on a calm-to-animated axis. Accepted values: `-2`, `-1`, `0`, `1`, `2`. `0` (the default) is the voice's tuned delivery and the production-validated setting, with `-2` the calm end of the range and `2` the animated end. Supported on all Flux voices; applies to the whole request. Beta: behavior may change in future model versions, and non-default values increase the risk of hallucinations and pronunciation errors; audition before shipping. An invalid value is rejected with a `400` — `EXPRESSIVITY_OUT_OF_RANGE` for a value outside the range, `EXPRESSIVITY_INCREMENT_INVALID` for a fractional value. See [Expressivity](/docs/tts-expressivity). sample_rate : typing.Optional[int] Sample Rate specifies the sample rate for the output audio. Based on the encoding, different sample rates are supported. For some encodings, the sample rate is not configurable speed : typing.Optional[float] Speaking rate multiplier that adjusts the pace of generated speech while preserving natural prosody and voice quality. Accepted values run `0.85` to `1.15` in `0.05` increments. Not yet supported in all languages. priority : typing.Optional[typing.Literal["low"]] Processing priority for asynchronous (callback) requests. The only supported value is low. 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[bytes] Returns the synthesized audio in the requested encoding as a binary stream. When a `callback` URL is supplied, the request is processed asynchronously and the response body is instead a JSON acknowledgement (Content-Type `application/json`) of the form {"request_id": "..."}, with the audio delivered to the callback URL. Because this endpoint is typed as a binary audio stream, SDK callers that set `callback` receive this JSON acknowledgement through the audio byte iterator as raw bytes and must join the chunks and parse `request_id` themselves. Examples -------- import asyncio from deepgram import AsyncDeepgramClient client = AsyncDeepgramClient( api_key="YOUR_API_KEY", ) async def main() -> None: await client.speak.v2.audio.generate( model="model", text="text", ) asyncio.run(main()) """ async with self._raw_client.generate( model=model, text=text, callback=callback, callback_method=callback_method, mip_opt_out=mip_opt_out, tag=tag, bit_rate=bit_rate, container=container, encoding=encoding, expressivity=expressivity, sample_rate=sample_rate, speed=speed, priority=priority, request_options=request_options, ) as r: async for _chunk in r.data: yield _chunk