speechify-api 2.0.1__tar.gz → 2.0.2__tar.gz

{speechify_api-2.0.1 → speechify_api-2.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: speechify-api
-Version: 2.0.1
+Version: 2.0.2
 Summary: Official Speechify API SDK
 Keywords: speechify,ai,api,sdk,text-to-speech,tts
 Author: Speechify
@@ -34,12 +34,12 @@ Project-URL: Homepage, https://docs.speechify.ai
 Project-URL: Repository, https://github.com/speechifyinc/speechify-api-sdk-python
 Description-Content-Type: text/markdown
 
-# Speechify Python Library
+# Speechifyinc Python Library
 
 [![fern shield](https://img.shields.io/badge/%F0%9F%8C%BF-Built%20with%20Fern-brightgreen)](https://buildwithfern.com?utm_source=github&utm_medium=github&utm_campaign=readme&utm_source=https%3A%2F%2Fgithub.com%2Fspeechifyinc%2Fspeechify-api-sdk-python)
 [![pypi](https://img.shields.io/pypi/v/speechify-api)](https://pypi.python.org/pypi/speechify-api)
 
-The Speechify Python library provides convenient access to the Speechify APIs from Python.
+The Speechifyinc Python library provides convenient access to the Speechifyinc APIs from Python.
 
 ## Table of Contents
 
@@ -50,7 +50,6 @@ The Speechify Python library provides convenient access to the Speechify APIs fr
 - [Environments](#environments)
 - [Async Client](#async-client)
 - [Exception Handling](#exception-handling)
-- [Pagination](#pagination)
 - [Advanced](#advanced)
   - [Access Raw Response Data](#access-raw-response-data)
   - [Retries](#retries)
@@ -80,7 +79,7 @@ Instantiate and use the client with the following:
 from speechify import Speechify
 
 client = Speechify(
-    token="<token>",
+    api_key="<token>",
 )
 
 client.audio.speech(
@@ -114,7 +113,7 @@ import asyncio
 from speechify import AsyncSpeechify
 
 client = AsyncSpeechify(
-    token="<token>",
+    api_key="<token>",
 )
 
 
@@ -145,29 +144,6 @@ except ApiError as e:
     print(e.body)
 ```
 
-## Pagination
-
-Paginated requests will return a `SyncPager` or `AsyncPager`, which can be used as generators for the underlying object.
-
-```python
-from speechify import Speechify
-
-client = Speechify(
-    token="<token>",
-)
-
-client.voices.list()
-```
-
-```python
-# You can also iterate through pages and access the typed response per page
-pager = client.voices.list(...)
-for page in pager.iter_pages():
-    print(page.response)  # access the typed response for each page
-    for item in page:
-        print(item)
-```
-
 ## Advanced
 
 ### Access Raw Response Data

{speechify_api-2.0.1 → speechify_api-2.0.2}/README.md

@@ -1,9 +1,9 @@
-# Speechify Python Library
+# Speechifyinc Python Library
 
 [![fern shield](https://img.shields.io/badge/%F0%9F%8C%BF-Built%20with%20Fern-brightgreen)](https://buildwithfern.com?utm_source=github&utm_medium=github&utm_campaign=readme&utm_source=https%3A%2F%2Fgithub.com%2Fspeechifyinc%2Fspeechify-api-sdk-python)
 [![pypi](https://img.shields.io/pypi/v/speechify-api)](https://pypi.python.org/pypi/speechify-api)
 
-The Speechify Python library provides convenient access to the Speechify APIs from Python.
+The Speechifyinc Python library provides convenient access to the Speechifyinc APIs from Python.
 
 ## Table of Contents
 
@@ -14,7 +14,6 @@ The Speechify Python library provides convenient access to the Speechify APIs fr
 - [Environments](#environments)
 - [Async Client](#async-client)
 - [Exception Handling](#exception-handling)
-- [Pagination](#pagination)
 - [Advanced](#advanced)
   - [Access Raw Response Data](#access-raw-response-data)
   - [Retries](#retries)
@@ -44,7 +43,7 @@ Instantiate and use the client with the following:
 from speechify import Speechify
 
 client = Speechify(
-    token="<token>",
+    api_key="<token>",
 )
 
 client.audio.speech(
@@ -78,7 +77,7 @@ import asyncio
 from speechify import AsyncSpeechify
 
 client = AsyncSpeechify(
-    token="<token>",
+    api_key="<token>",
 )
 
 
@@ -109,29 +108,6 @@ except ApiError as e:
     print(e.body)
 ```
 
-## Pagination
-
-Paginated requests will return a `SyncPager` or `AsyncPager`, which can be used as generators for the underlying object.
-
-```python
-from speechify import Speechify
-
-client = Speechify(
-    token="<token>",
-)
-
-client.voices.list()
-```
-
-```python
-# You can also iterate through pages and access the typed response per page
-pager = client.voices.list(...)
-for page in pager.iter_pages():
-    print(page.response)  # access the typed response for each page
-    for item in page:
-        print(item)
-```
-
 ## Advanced
 
 ### Access Raw Response Data

{speechify_api-2.0.1 → speechify_api-2.0.2}/pyproject.toml

@@ -1,10 +1,10 @@
 [project]
 name = "speechify-api"
-dynamic = ["version"]
+version = "2.0.2"
 
 [tool.poetry]
 name = "speechify-api"
-version = "2.0.1"
+version = "2.0.2"
 description = "Official Speechify API SDK"
 readme = "README.md"
 authors = [

{speechify_api-2.0.1 → speechify_api-2.0.2}/src/speechify/__init__.py

@@ -7,8 +7,12 @@ from importlib import import_module
 
 if typing.TYPE_CHECKING:
     from .types import (
-        AudioOutputFormat,
-        AudioStreamOutputFormat,
+        CreateVoiceLanguage,
+        CreateVoiceModel,
+        CreateVoiceModelName,
+        CreatedVoice,
+        CreatedVoiceGender,
+        CreatedVoiceType,
         Error,
         ErrorCode,
         ErrorDetail,
@@ -22,15 +26,12 @@ if typing.TYPE_CHECKING:
         GetVoiceType,
         GetVoicesModel,
         GetVoicesModelName,
-        ListVoicesResponse,
         NestedChunk,
-        PaginationMeta,
         SpeechMarks,
     )
     from .errors import (
         BadGatewayError,
         BadRequestError,
-        ConflictError,
         ForbiddenError,
         InternalServerError,
         NotFoundError,
@@ -54,12 +55,15 @@ if typing.TYPE_CHECKING:
     from .voices import CreateVoicesRequestGender
 _dynamic_imports: typing.Dict[str, str] = {
     "AsyncSpeechify": ".client",
-    "AudioOutputFormat": ".types",
-    "AudioStreamOutputFormat": ".types",
     "BadGatewayError": ".errors",
     "BadRequestError": ".errors",
-    "ConflictError": ".errors",
+    "CreateVoiceLanguage": ".types",
+    "CreateVoiceModel": ".types",
+    "CreateVoiceModelName": ".types",
     "CreateVoicesRequestGender": ".voices",
+    "CreatedVoice": ".types",
+    "CreatedVoiceGender": ".types",
+    "CreatedVoiceType": ".types",
     "DefaultAioHttpClient": "._default_clients",
     "DefaultAsyncHttpxClient": "._default_clients",
     "Error": ".types",
@@ -80,10 +84,8 @@ _dynamic_imports: typing.Dict[str, str] = {
     "GetVoicesModel": ".types",
     "GetVoicesModelName": ".types",
     "InternalServerError": ".errors",
-    "ListVoicesResponse": ".types",
     "NestedChunk": ".types",
     "NotFoundError": ".errors",
-    "PaginationMeta": ".types",
     "PaymentRequiredError": ".errors",
     "ServiceUnavailableError": ".errors",
     "SpeechMarks": ".types",
@@ -122,12 +124,15 @@ def __dir__():
 
 __all__ = [
     "AsyncSpeechify",
-    "AudioOutputFormat",
-    "AudioStreamOutputFormat",
     "BadGatewayError",
     "BadRequestError",
-    "ConflictError",
+    "CreateVoiceLanguage",
+    "CreateVoiceModel",
+    "CreateVoiceModelName",
     "CreateVoicesRequestGender",
+    "CreatedVoice",
+    "CreatedVoiceGender",
+    "CreatedVoiceType",
     "DefaultAioHttpClient",
     "DefaultAsyncHttpxClient",
     "Error",
@@ -148,10 +153,8 @@ __all__ = [
     "GetVoicesModel",
     "GetVoicesModelName",
     "InternalServerError",
-    "ListVoicesResponse",
     "NestedChunk",
     "NotFoundError",
-    "PaginationMeta",
     "PaymentRequiredError",
     "ServiceUnavailableError",
     "SpeechMarks",

{speechify_api-2.0.1 → speechify_api-2.0.2}/src/speechify/audio/client.py

@@ -4,8 +4,6 @@ import typing
 
 from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
-from ..types.audio_output_format import AudioOutputFormat
-from ..types.audio_stream_output_format import AudioStreamOutputFormat
 from ..types.get_speech_options_request import GetSpeechOptionsRequest
 from ..types.get_speech_response import GetSpeechResponse
 from ..types.get_stream_options_request import GetStreamOptionsRequest
@@ -43,15 +41,12 @@ class AudioClient:
         language: typing.Optional[str] = OMIT,
         model: typing.Optional[GetSpeechRequestModel] = OMIT,
         options: typing.Optional[GetSpeechOptionsRequest] = OMIT,
-        output_format: typing.Optional[AudioOutputFormat] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> GetSpeechResponse:
         """
         Synthesize speech audio from text or SSML. Returns the complete audio
         file plus billing and speech-mark metadata in a single JSON response.
         For low-latency playback or long-form text, use POST /v1/audio/stream.
-        Set `output_format` for explicit sample-rate/bitrate control (e.g.
-        `pcm_16000` or `ulaw_8000` for telephony).
 
         Parameters
         ----------
@@ -71,13 +66,10 @@ class AudioClient:
             Please refer to the list of the supported languages and recommendations regarding this parameter: https://docs.speechify.ai/docs/language-support.
 
         model : typing.Optional[GetSpeechRequestModel]
-            Model used for audio synthesis. `simba-english` is optimized for English, `simba-multilingual` for non-English or mixed input. `simba-3.2` is the streaming-native model with lower TTFB and richer expressivity, and the recommended Simba 3 model. `simba-3.0` is the earlier Simba 3.0 model, still available. `simba-3.0` and `simba-3.2` are currently English only; multilingual coming soon, and non-English voices return 400 until it ships.
+            Model used for audio synthesis. `simba-english` is optimized for English, `simba-multilingual` for non-English or mixed input. `simba-3.0` is the streaming-native model with lower TTFB and richer expressivity. Currently English only; multilingual coming soon. Non-English voices return 400 until multilingual support ships.
 
         options : typing.Optional[GetSpeechOptionsRequest]
 
-        output_format : typing.Optional[AudioOutputFormat]
-            The output audio format as a `codec_sampleRate_bitrate` string. Takes precedence over `audio_format` when set.
-
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -91,8 +83,7 @@ class AudioClient:
         from speechify import Speechify
 
         client = Speechify(
-            "2026-07-07",
-            token="YOUR_TOKEN",
+            api_key="YOUR_API_KEY",
         )
         client.audio.speech(
             audio_format="mp3",
@@ -108,7 +99,6 @@ class AudioClient:
             language=language,
             model=model,
             options=options,
-            output_format=output_format,
             request_options=request_options,
         )
         return _response.data
@@ -116,26 +106,29 @@ class AudioClient:
     def stream(
         self,
         *,
+        accept: StreamAudioRequestAccept,
         input: str,
         voice_id: str,
-        accept: typing.Optional[StreamAudioRequestAccept] = None,
         language: typing.Optional[str] = OMIT,
         model: typing.Optional[GetStreamRequestModel] = OMIT,
         options: typing.Optional[GetStreamOptionsRequest] = OMIT,
-        output_format: typing.Optional[AudioStreamOutputFormat] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[bytes]:
         """
         Synthesize speech and stream the audio back as it is generated, for
-        low-latency playback. Set `output_format` in the body for explicit
-        codec/sample-rate/bitrate control (e.g. `pcm_16000` or `ulaw_8000` for
-        telephony), or fall back to the Accept header for the container; the
-        response is raw audio bytes (HTTP chunked). For Base64-encoded audio
-        with speech-mark metadata in a single JSON response, use
+        low-latency playback. The Accept header selects the audio container;
+        the response is raw audio bytes (HTTP chunked). For Base64-encoded
+        audio with speech-mark metadata in a single JSON response, use
         POST /v1/audio/speech.
 
         Parameters
         ----------
+        accept : StreamAudioRequestAccept
+            Selects the audio container/codec for the streamed response. The
+            response Content-Type echoes this value, except `audio/pcm` returns
+            `audio/L16` with rate and channels parameters (raw 16-bit linear
+            PCM, 24 kHz mono, little-endian).
+
         input : str
             Plain text or SSML to be synthesized to speech.
             Refer to https://docs.speechify.ai/docs/api-limits for the input size limits.
@@ -144,60 +137,43 @@ class AudioClient:
         voice_id : str
             Id of the voice to be used for synthesizing speech. Refer to /v1/voices endpoint for available voices
 
-        accept : typing.Optional[StreamAudioRequestAccept]
-            Selects the audio container/codec for the streamed response when
-            `output_format` is not set in the request body. The response
-            Content-Type echoes this value, except `audio/pcm` returns
-            `audio/L16` with rate and channels parameters (raw 16-bit linear
-            PCM, 24 kHz mono, little-endian). For explicit sample-rate/bitrate
-            control (e.g. `pcm_16000`, `ulaw_8000`), set `output_format` in the
-            body instead; it takes precedence over this header.
-
         language : typing.Optional[str]
             Language of the input. Follow the format of an ISO 639-1 language code and an ISO 3166-1 region code, separated by a hyphen, e.g. en-US.
             Please refer to the list of the supported languages and recommendations regarding this parameter: https://docs.speechify.ai/docs/language-support.
 
         model : typing.Optional[GetStreamRequestModel]
-            Model used for audio synthesis. `simba-english` is optimized for English, `simba-multilingual` for non-English or mixed input. `simba-3.2` is the streaming-native model with lower TTFB and richer expressivity, and the recommended Simba 3 model. `simba-3.0` is the earlier Simba 3.0 model, still available. `simba-3.0` and `simba-3.2` are currently English only; multilingual coming soon, and non-English voices return 400 until it ships.
+            Model used for audio synthesis. `simba-english` is optimized for English, `simba-multilingual` for non-English or mixed input. `simba-3.0` is the streaming-native model with lower TTFB and richer expressivity. Currently English only; multilingual coming soon. Non-English voices return 400 until multilingual support ships.
 
         options : typing.Optional[GetStreamOptionsRequest]
 
-        output_format : typing.Optional[AudioStreamOutputFormat]
-            The output audio format as a `codec_sampleRate_bitrate` string. Takes precedence over the `Accept` header when set, so you can request formats the `Accept` enum does not cover (e.g. `pcm_16000`, `ulaw_8000`). `wav_*` formats are not supported on streaming - use `POST /v1/audio/speech` for wav.
-
         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]
-            Streamed audio. When `output_format` is set it selects the
-            codec/sample rate; otherwise the Accept header does. The
-            Content-Type reflects the selected format: it matches the Accept
-            header, except raw PCM returns `audio/L16` (with rate and channels
-            parameters) and u-law returns `audio/basic`.
+            Chunked audio stream for the requested input.
 
         Examples
         --------
         from speechify import Speechify
 
         client = Speechify(
-            "2026-07-07",
-            token="YOUR_TOKEN",
+            api_key="YOUR_API_KEY",
         )
         client.audio.stream(
+            accept="audio/mpeg",
             input="input",
             voice_id="voice_id",
         )
         """
         with self._raw_client.stream(
+            accept=accept,
             input=input,
             voice_id=voice_id,
-            accept=accept,
             language=language,
             model=model,
             options=options,
-            output_format=output_format,
             request_options=request_options,
         ) as r:
             yield from r.data
@@ -227,15 +203,12 @@ class AsyncAudioClient:
         language: typing.Optional[str] = OMIT,
         model: typing.Optional[GetSpeechRequestModel] = OMIT,
         options: typing.Optional[GetSpeechOptionsRequest] = OMIT,
-        output_format: typing.Optional[AudioOutputFormat] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> GetSpeechResponse:
         """
         Synthesize speech audio from text or SSML. Returns the complete audio
         file plus billing and speech-mark metadata in a single JSON response.
         For low-latency playback or long-form text, use POST /v1/audio/stream.
-        Set `output_format` for explicit sample-rate/bitrate control (e.g.
-        `pcm_16000` or `ulaw_8000` for telephony).
 
         Parameters
         ----------
@@ -255,13 +228,10 @@ class AsyncAudioClient:
             Please refer to the list of the supported languages and recommendations regarding this parameter: https://docs.speechify.ai/docs/language-support.
 
         model : typing.Optional[GetSpeechRequestModel]
-            Model used for audio synthesis. `simba-english` is optimized for English, `simba-multilingual` for non-English or mixed input. `simba-3.2` is the streaming-native model with lower TTFB and richer expressivity, and the recommended Simba 3 model. `simba-3.0` is the earlier Simba 3.0 model, still available. `simba-3.0` and `simba-3.2` are currently English only; multilingual coming soon, and non-English voices return 400 until it ships.
+            Model used for audio synthesis. `simba-english` is optimized for English, `simba-multilingual` for non-English or mixed input. `simba-3.0` is the streaming-native model with lower TTFB and richer expressivity. Currently English only; multilingual coming soon. Non-English voices return 400 until multilingual support ships.
 
         options : typing.Optional[GetSpeechOptionsRequest]
 
-        output_format : typing.Optional[AudioOutputFormat]
-            The output audio format as a `codec_sampleRate_bitrate` string. Takes precedence over `audio_format` when set.
-
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -277,8 +247,7 @@ class AsyncAudioClient:
         from speechify import AsyncSpeechify
 
         client = AsyncSpeechify(
-            "2026-07-07",
-            token="YOUR_TOKEN",
+            api_key="YOUR_API_KEY",
         )
 
 
@@ -300,7 +269,6 @@ class AsyncAudioClient:
             language=language,
             model=model,
             options=options,
-            output_format=output_format,
             request_options=request_options,
         )
         return _response.data
@@ -308,26 +276,29 @@ class AsyncAudioClient:
     async def stream(
         self,
         *,
+        accept: StreamAudioRequestAccept,
         input: str,
         voice_id: str,
-        accept: typing.Optional[StreamAudioRequestAccept] = None,
         language: typing.Optional[str] = OMIT,
         model: typing.Optional[GetStreamRequestModel] = OMIT,
         options: typing.Optional[GetStreamOptionsRequest] = OMIT,
-        output_format: typing.Optional[AudioStreamOutputFormat] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[bytes]:
         """
         Synthesize speech and stream the audio back as it is generated, for
-        low-latency playback. Set `output_format` in the body for explicit
-        codec/sample-rate/bitrate control (e.g. `pcm_16000` or `ulaw_8000` for
-        telephony), or fall back to the Accept header for the container; the
-        response is raw audio bytes (HTTP chunked). For Base64-encoded audio
-        with speech-mark metadata in a single JSON response, use
+        low-latency playback. The Accept header selects the audio container;
+        the response is raw audio bytes (HTTP chunked). For Base64-encoded
+        audio with speech-mark metadata in a single JSON response, use
         POST /v1/audio/speech.
 
         Parameters
         ----------
+        accept : StreamAudioRequestAccept
+            Selects the audio container/codec for the streamed response. The
+            response Content-Type echoes this value, except `audio/pcm` returns
+            `audio/L16` with rate and channels parameters (raw 16-bit linear
+            PCM, 24 kHz mono, little-endian).
+
         input : str
             Plain text or SSML to be synthesized to speech.
             Refer to https://docs.speechify.ai/docs/api-limits for the input size limits.
@@ -336,38 +307,22 @@ class AsyncAudioClient:
         voice_id : str
             Id of the voice to be used for synthesizing speech. Refer to /v1/voices endpoint for available voices
 
-        accept : typing.Optional[StreamAudioRequestAccept]
-            Selects the audio container/codec for the streamed response when
-            `output_format` is not set in the request body. The response
-            Content-Type echoes this value, except `audio/pcm` returns
-            `audio/L16` with rate and channels parameters (raw 16-bit linear
-            PCM, 24 kHz mono, little-endian). For explicit sample-rate/bitrate
-            control (e.g. `pcm_16000`, `ulaw_8000`), set `output_format` in the
-            body instead; it takes precedence over this header.
-
         language : typing.Optional[str]
             Language of the input. Follow the format of an ISO 639-1 language code and an ISO 3166-1 region code, separated by a hyphen, e.g. en-US.
             Please refer to the list of the supported languages and recommendations regarding this parameter: https://docs.speechify.ai/docs/language-support.
 
         model : typing.Optional[GetStreamRequestModel]
-            Model used for audio synthesis. `simba-english` is optimized for English, `simba-multilingual` for non-English or mixed input. `simba-3.2` is the streaming-native model with lower TTFB and richer expressivity, and the recommended Simba 3 model. `simba-3.0` is the earlier Simba 3.0 model, still available. `simba-3.0` and `simba-3.2` are currently English only; multilingual coming soon, and non-English voices return 400 until it ships.
+            Model used for audio synthesis. `simba-english` is optimized for English, `simba-multilingual` for non-English or mixed input. `simba-3.0` is the streaming-native model with lower TTFB and richer expressivity. Currently English only; multilingual coming soon. Non-English voices return 400 until multilingual support ships.
 
         options : typing.Optional[GetStreamOptionsRequest]
 
-        output_format : typing.Optional[AudioStreamOutputFormat]
-            The output audio format as a `codec_sampleRate_bitrate` string. Takes precedence over the `Accept` header when set, so you can request formats the `Accept` enum does not cover (e.g. `pcm_16000`, `ulaw_8000`). `wav_*` formats are not supported on streaming - use `POST /v1/audio/speech` for wav.
-
         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]
-            Streamed audio. When `output_format` is set it selects the
-            codec/sample rate; otherwise the Accept header does. The
-            Content-Type reflects the selected format: it matches the Accept
-            header, except raw PCM returns `audio/L16` (with rate and channels
-            parameters) and u-law returns `audio/basic`.
+            Chunked audio stream for the requested input.
 
         Examples
         --------
@@ -376,13 +331,13 @@ class AsyncAudioClient:
         from speechify import AsyncSpeechify
 
         client = AsyncSpeechify(
-            "2026-07-07",
-            token="YOUR_TOKEN",
+            api_key="YOUR_API_KEY",
         )
 
 
         async def main() -> None:
             await client.audio.stream(
+                accept="audio/mpeg",
                 input="input",
                 voice_id="voice_id",
             )
@@ -391,13 +346,12 @@ class AsyncAudioClient:
         asyncio.run(main())
         """
         async with self._raw_client.stream(
+            accept=accept,
             input=input,
             voice_id=voice_id,
-            accept=accept,
             language=language,
             model=model,
             options=options,
-            output_format=output_format,
             request_options=request_options,
         ) as r:
             async for _chunk in r.data: