Version 3.8.1

Lots of changes since June! Summary below. Get all of these and more with a quick pip install --upgrade SpeechRecognition.

• Snowboy hotwords support for highly efficient, performant listening (thanks @beeedy!). This is implemented as the snowboy_configuration parameter of recognizer_instance.listen.
• Configurable Pocketsphinx models - you can now specify your own acoustic parameters, language model, and phoneme dictionary, using the language parameter of recognizer_instance.recognize_sphinx (thanks @frawau!).
• audio_data_instance.get_segment(start_ms=None, end_ms=None) is a new method that can be called on any AudioData instance to get a segment of the audio starting at start_ms and ending at end_ms. This is really useful when you want to get, say, only the first five seconds of some audio.
• The stopper function returned by listen_in_background now accepts one parameter, wait_for_stop (defaulting to True for backwards compatibility), which determines whether the function will wait for the background thread to fully shutdown before returning. One advantage is that if wait_for_stop is False, you can call the stopper function from any thread!
• New example, demonstrating how to simultaneously listen to and recognize speech with the threaded producer/consumer pattern: threaded_workers.py.
• Various improvements and bugfixes:
  • Python 3 style type annotations in library documentation.
  • recognize_google_cloud now uses the v1 rather than the beta API (thanks @oort7!).
  • recognize_google_cloud now returns timestamp info when the show_all parameter is True.
  • recognize_bing won't time out as often on credential requests, due to a longer default timeout.
  • recognize_google_cloud timeouts respect recognizer_instance.operation_timeout now (thanks @reefactor!).
  • Any recognizers using FLAC audio were broken inside Linux on Docker - this is now fixed (thanks @reefactor!).
  • Various documentation and lint fixes (thanks @josh-hernandez-exe!).
  • Lots of small build system improvements.

Version 3.7.1

As usual, get it with pip install --upgrade SpeechRecognition

• New grammar parameter for recognizer_instance.recognize_sphinx - now, you can specify a JSGF or FSG grammar to PocketSphinx (thanks @aleneum!).
• Update PyAudio to version 0.2.11 - this fixes a couple memory management issues users have been experiencing.
• Update FLAC to 1.3.2 on all platforms - this will make it easier to support more audio formats in the near future.
• Fixes for various APIs on Python 3.6+ - small changes in urllib.request behavior made requests fail in certain situations.
• Fixes for Bing Speech API timing out due to some backwards incompatible changes to their API.
• Restore original IBM audio segmentation behaviour - previously, it would stop recognizing after the first pause. Now, it will recognize all speech in the input audio, as it did before IBM's changes.
• Fix links in PocketSphinx docs and library reference. Add-on language models now available from Google Drive, including the now-officially-supported Italian model.
• New troubleshooting entries for JACK server in README.
• Documentation and build process updates.

Version 3.6.5

Quick bugfix for PortableNamedTemporaryFile:

• Fix file descriptor opening on Python 2.
• Add tests for Sphinx keyword matching.

Version 3.6.4

Bugfix release!

• Fix tempfile.NamedTemporaryFile on Windows, by replacing it with a PortableNamedTemporaryFile class. Previously, it didn't necessarily support the file being re-opened after originally opened.
• Documentation/troubleshooting improvements (thanks @hassanmian!).
• Add support for 24-bit FLAC audio files (thanks @sudevschiz!).
• Fix phrase_time_limit being ignored for listen_in_background (thanks @dodysw!)
• Added lots of new audio regression tests.
• Code cleanup for tests and examples.

Version 3.6.3

Small bugfix release:

• Handle case when GSR doesn't return a confidence value (thanks @jcsilva!).
• Config, style, and release improvements.
• Fix console window sometimes popping up when on Windows (thanks @Qdrew!)
• Switch release over to universal Wheels rather than source distribution.

Version 3.6.0

This is more of a maintenance release, but a few features slipped in as well:

• Support for the Google Cloud Speech API with recognizer_instance.recognize_google_cloud (thanks @Thynix!), plus documentation and examples.
• Automatic sample rate detection in speech_recognition.Microphone - this should fully resolve all the "Invalid sample rate" issues from PyAudio.
• Project now has automated tests and continuous integration with TravisCI. It's pretty nifty, and has already caught a few things during development!
• Keywords example for recognizer_instance.recognize_sphinx.
• Documentation improvements and updated advice in troubleshooting and library reference.
• Bugfix - Google Speech Recognition sometimes didn't return the text with the highest confidence (thanks @akabraham!).
• Bugfix - EOFError upon encountering malformed audio files; a proper exception message is now given.
• Updated FLAC binaries for OS X.
• Bugfix - invalid FLAC binary path on OS X (thanks @akabraham!).
• Code cleanup.

Version 3.5.0

• Support for the Houndify API with recognizer_instance.recognize_houndify (thanks @tb0hdan!).
• recognize_sphinx now supports keyword-based matching via the keywords=[("cat", 30), ("potato", 45)] parameter.
  • The second number in each pair is the sensitivity, which determines how loosely Sphinx will interpret speech to be those keywords - higher numbers mean more false positives, while lower numbers mean a lower detection rate.
  • A new example for keyword matching is now available.
• BREAKING CHANGE: API.AI STT API IS BEING SHUT DOWN SOON. (source)
  • For now, the recognize_api function will keep working if you're on a paid API.AI plan, and we will not be removing it until the service is shut down entirely.
  • It is best to transition to another backend as soon as possible. I recommend Microsoft Bing Voice Recognition or Wit.ai for previous API.AI users.
• phrase_time_limit option for listening functions, to limit phrase lengths to a certain number of seconds.
• Support for operation timeouts with recognizer_instance.operation_timeout - this can be used to ensure long requests always take finite time.
• recognize_ibm now opts out of request logging by default, for improved user privacy (thanks @michellemorales!). This is a breaking change if you previously relied on request logging behaviour.
• Bugfix - listen() sometimes didn't terminate on finite-length streams.
• Bugfix - Microsoft Bing Voice Recognition changed their authentication API endpoint, so that required some small code updates (thanks @tmator!).
• Bugfix - 24-bit audio now works correctly on Python 2.
• Update Wit.ai API version from deprecated version.
• A bunch of documentation updates, fixes, and improvements.

Version 3.4.6

Bugfix release.

Changes:

• api.ai now requires the sessionId field, so we'll just add that in (thanks @jhoelzl!).
• Improve documentation a bit.
• Various other small fixes.

Version 3.4.5

Changes:

• Bug fix: non-24-bit audio wasn't converted properly to 16-bit audio on Python 2, due to the new 24-bit audio shim. Thanks to @jhoelzl for reporting!

Version 3.4.4

Maintenance release:

• Python versions less than 3.4 don't support 24-bit audio properly. We now have pure-Python shims that will allow 24-bit audio to work on those old Python versions, though they will be somewhat slower. Thanks to @danse for reporting the issue!
• Added updated Pocketsphinx binaries and Pocketsphinx installation procedures to match improvements on their end.
• Fix Unicode file paths on Windows.
• Fix caching in recognizer_instance.recognize_bing.
• We now use the Manylinux Docker image for building FLAC. Hopefully, this will make building universal Linux binaries easier for packagers.