Release Notes

Learn more about how we manage releases for Media API versions.

2021-02-08

We've released new updates to the following services:

Media Analyze

Changelog:

  • Added:

    • Processed Region as part of the output schema now reports information the Start and End times of the content used for analysis.
    • Output schema documentation is available as part of Analyze API spec.
  • Changed:

    • Minimum file duration of 1.8 seconds of content can be analyzed. Previous versions minimum file duration was 1 second.

2021-01-11

We've released new updates to the following services:

Media Enhance

Changelog:

  • New Speech Plosive reduction detects and reduces excessive plosive sounds within speech -- typically caused when the letter P and B is spoken too close to a microphone.

Media Analyze

The b1.3 beta release introduces a new method for receiving content summary, event and time series analysis results. With the introduction of this new output format we have also deprecated the previous v1.1 version of the API.

Changelog:

  • Analyze requests now require a URL to a writable location where Analyze API will write the results. The results are no longer available in the response of GET command.
  • Clipping data reports the locations of clipped sections, enabling you to quickly identify areas within the file that have been recorded to a full scale level (which often indicates distortion).
  • Loudness time series data is now added, giving loudness, sample peak and true peak values for every second of the media file. This can be used to understand the locations of loud and quiet sections and the journey of dynamics in a media file.
  • Audio sections for content type are now returned, reporting the location of music, speech and silence sections within a file. Each section includes:

    • Start time - the time index (in seconds) when a section starts within the media file
    • Duration - length of a section (in seconds)
  • Music Sectional Analysis For each section of music, deeper analysis is now returned to provide directional information. Due to the complex nature of music and its varied expressions, this data should be used only as guidance.

    • Genre - the musical genre of a section of music
    • Era - the decade that a section of music evokes
    • Tempo - the speed or pace (as beats per minute) of a section of music
    • Key - the musical key of a section of music
    • Instrumentation - the top three instruments detected in a section of music

2020-11-23

We've released new updates to the following services:

Changelog:

  • We have made speech tonality improvements to the Dynamic EQ feature in this release. With these improvements speech sounds more natural and consistent throughout the media, especially for content with multiple talkers and varying vocal characteristics.
  • We have made performance improvements so that Enhance processes faster for all files, most notably for large files.

2020-10-02

We've released new updates to the following services:

Changelog:

  • The content types supported by the Media Enhance API have been expanded to give processing additional guidance on how to tune the results. Each content.type configures the audio parameters automatically to apply processing that is most suitable to the characteristics typical of that type of recording.

    • If you don't specify a content.type the algorithm will choose an estimated best fit but for better results the type should be identified as an input parameter.
    • New processing profiles have been added based on these types:

      • studio - for recordings captured in a controlled studio-like environment. Generally, the subjects are close to the microphone with minimal background noise.
      • mobile_phone - where the recording was captured on a mobile phone. Frequently, the subject is giving priority to the camera in recording a video which is not an optimal position for the microphone and sound capture.
      • voice_recording - may also be on a mobile device, but voice is the priority and other sounds seen as a distraction.
      • conference - includes recordings where there are multiple talkers in a larger room setting
      • Note that voice-over has been renamed to voice_over.
    • Adjusting a specific audio attribute will take precedence over the setting applied from the content type chosen.
  • Noise reduction has made significant improvements in performance for cases where the background noise is changing dynamically. This improves content where:

    • The environmental noise is changing over time, eg. talkers who are moving around within a location so sometimes closer or further away from a microphone or source of noise.
    • Multiple talkers with different background noise levels have been cut together. This is especially prevalent in content using video conferencing to connect multiple remote guests or presenters.
  • Improved accuracy of progress reporting returned when getting the status of a job. The progress percentage is now updated more frequently to provide a better indication of how much of the input file has been processed.

2020-09-15

We've released new updates to the following services:

Changelog:

  • With this release you can now get more insight into the scenes present in your media. The Analyze API response includes a breakdown reporting Speech, Music, Silence, and Other sections so that you can get an understanding of the percentage and num_sections identifying the count of discrete sections attributable to each type. A section is defined to be a consecutive block of a section type that is at least 0.5 seconds long.
  • The presence of clipping has been identified as the number of discrete sections within the content. You can find this as the num_sections attribute and the num_events is no longer provided.
  • Some general performance improvements have been made for media files with a duration greater than 30 minutes. If your media is not long enough to be analyzed you will get an invalid-input-file error.
  • The start and end timestamps for detected silence segments have been removed. If you relied on this functionality, please contact Support and we can discuss a beta preview of how this functionality will be changing in a future release.
  • The loudness validation results will only be returned going forward if you specify a specific loudness profile in your request.

2020-08-06

We've released new updates to the following services:

Changelog:

  • We've introduced a new audio filter for Hum Reduction. The API can now detect and remove undesirable noise such as electrical hum, constant background tones, or soft/low frequency humming. The Hum Reduction filter is on by default and can be disabled.
  • The Dynamic EQ filter now has an enable/disable parameter. This parameter allows you to disable dynamics and equalization processing in the case where you only want to process noise or loudness.
  • The Speech Isolation filter has been tuned to provide stronger speech isolation when the amount is set between 80-100". These stronger Speech Isolation values may sometimes trade off speech quality for better intelligibility in very noisy content.
  • We've made across the board performance improvements so that Enhance processes faster, most noticeable for larger files.

2020-06-18

We've released new updates to the following services:

Changelog:

  • api_version can now be viewed in GET responses for all services
  • Improved speech clarity and tone in both dry and reverberant acoustic environments. There is less high frequency roll off and less suppression of the reverb tail.
  • For talkers who were not close mic'd or speaking from a far distance from the microphone, voices are brought forward which allows noise reduction to be more effective while preserving natural speech.
  • Stationary background noise attributed to HVAC is quieter now for more content types.

Read more in Enhance Audio by Removing Stationary Background Noise.

2020-05-12

We've released new updates to the following services:

Changelog:

  • Services now generally available

Read more Welcome to Dolby.io.