Releases: AssemblyAI/assemblyai-python-sdk
Releases · AssemblyAI/assemblyai-python-sdk
0.34.0
What's Changed
Features
- Add missing
context
parameter for LeMUR task by @ploeber in #91 - Add parameter to select audio input device when streaming from microphone by @mjshiggins in #82
Improvements
- Fix mypy typing errors by @ploeber in #91:
- Add correct types in
types.py
,api.py
, andlemur.py
- Correct usage of
httpx.codes.OK
instead ofhttpx.codes.ok
- Remove
context
property fromLemurSource
sinceself._context
does not exist
- Add correct types in
- Remove
httpx_mock.reset(False)
in the unit tests (the interface changed and is no longer supported in Python >= 3.9) - Add GitHub Action
lint.yml
with ruff formating and mypy checks by @ploeber in #85
New Contributors
- @mjshiggins made their first contribution in #82
Full Changelog: 0.33.0...0.34.0
0.33.0
Changes
Features
- New ALD features by @ploeber in #83:
- Add
language_confidence_threshold
as a configuration parameter and as a JSON response field - Add
language_confidence
as a JSON response field
- Add
Improvements
- Remove SDK-side value validation in
speech_threshold.setter
to align with thelanguage_confidence_threshold
behavior. This lets the API handle possible errors.
Full Changelog: 0.32.0...0.33.0
0.32.0
What's Changed
Features
- Add new
RealtimeError
codes and avoidKeyError
if the code is unsupported - Add optional parameter
return_failures
totranscribe_group()
andTranscriptGroup.transcribe()
. If set toTrue
, the function also returns a list of error messages for failed transcription jobs.
Improvements
- Raise Exception to user for
get_by_id()
andwait_for_completion()
and no longer create a misleading invalid transcript object
Full Changelog: 0.31.0...0.32.0
0.31.0
What's Changed
Features
- Adds support to list transcripts (#57 ):
- Adds functions
Transcriber.list_transcripts()
andTranscriber.list_transcripts_async()
- Adds new types
ListTranscriptParameters
,PageDetails
,ListTranscriptResponse
, andTranscriptItem
- Adds functions
Removals
- Removes
conformer-2
fromSpeechModel
enum
Documentation
- Adds
list_transcript()
examples to README, including an example that shows how to paginate
Full Changelog: 0.30.0...0.31.0
0.30.0
What's Changed
Features
- Add new LeMUR models by @ploeber in #75:
- Claude 3.5 Sonnet (
LemurModel.claude3_5_sonnet
) - Claude 3 Opus (
LemurModel.claude3_opus
) - Claude 3 Haiku (
LemurModel.claude3_haiku
) - Claude 3 Sonnet (
LemurModel.claude3_sonnet
)
- Claude 3.5 Sonnet (
Full Changelog: 0.29.0...0.30.0
0.29.0
0.28.1
0.28.0
What's Changed
Features
- Add LeMUR methods
get_response_data()
andget_response_data_async()
:- Allows to retrieve a LeMUR response that was previously generated
- Add new LeMUR response field
usage
:- Contains information about used input tokens and output tokens for LeMUR calls
- Add new generic Lemur response type
LemurStringResponse
- Add
__version__.py
. The version number can now we accessed withaai.__version__
Improvements
- Raise Exception to user if file uploading fails and no longer create a misleading invalid transcript object
Chore
- Include info about SDK version and Python version in user agent
Full Changelog: 0.27.0...0.28.0
0.27.0
What's Changed
Features
- Add new values for
EntityType
. Entity detection and PII redaction now support more entities. This also fixes potential validation errors that could have occurred with previous versions. by @ploeber in #71
Full Changelog: 0.26.0...0.27.0
0.26.0
What's Changed
Features
- Add support for file uploads through
Transcriber.upload()
andTranscriber.upload_async()
in #68 - Add support for
BinaryIO
type forsubmit()
andtranscribe()
in #68 - Add support for
redact_pii_audio_quality
by @dweekly in #66
Deprecation
- Deprecate
extras.file_from_stream
. The new upload functions can be used instead.
New Contributors
Full Changelog: 0.25.0...0.26.0