1.2.2

What's Changed

• 🌿 Fern Regeneration -- February 3, 2025 by @fern-api in #62

Full Changelog: 1.2.1...1.2.2

1.2.1

What's Changed

• 🌿 Fern Regeneration -- January 21, 2025 by @fern-api in #61

Full Changelog: 1.2.0...1.2.1

1.2.0

What's Changed

• 🌿 Fern Regeneration -- October 17, 2024 by @fern-api in #55
  • ⚠️ ListTranscriptParams.Limit type has changed from long to int
  • Add Multichannel property to TranscriptParams
  • Add Multichannel and AudioChannels properties to Transcript
  • Add Channel property to TranscriptWord, TranscriptUtterance, TranscriptSentence, and SentimentAnalysisResult
  • Add LemurModel.AnthropicClaude2_0
  • Deprecate LemurModel.AnthropicClaude2
  • Update StringEnumSerializer to support duplicate enum string values (AnthropicClaude2_0 and AnthropicClaude2)
  • Updated XML docs
• Fix content safety model parsing by @Swimburger in #56

Full Changelog: 1.1.4...1.2.0

1.1.4

Full Changelog: 1.1.3...1.1.4

1.1.3

Full Changelog: 1.1.2...1.1.3

1.1.2

What's Changed

• Make JsonUtils public by @Swimburger in #53
• Add clone to TranscriptParams and TranscriptOptionalParams by @Swimburger in #54

Full Changelog: 1.1.1...1.1.2

1.1.1

What's Changed

• 🌿 Fern Regeneration -- August 26, 2024 by @fern-api in #47
• Add optional request options and cancellation tokens to extended clients by @Swimburger in #48
• feat: Add XML docs by @Swimburger in #50
• Add overloads to upload files using byte array and memory by @Swimburger in #51

Full Changelog: 1.1.0...1.1.1

1.1.0

What's Changed

• Add more overloads to upload files, submit, and transcribe by @Swimburger in #45
• Make Microphone stream sample Windows compatible, add readmes by @Swimburger in #44
• Add LanguageConfidenceThreshold to Transcript, TranscriptParams, and TranscriptOptionalParams.

  The confidence threshold for the automatically detected language.
  An error will be returned if the language confidence is below this threshold.

• Add LanguageConfidence to Transcript

  The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence)

Using these new fields you can determine the confidence of the language detection model (enable by setting LanguageDetection to true), and fail the transcript if it doesn't meet your desired threshold.

Learn more about the new automatic language detection model and feature improvements on our blog.

Full Changelog: 1.0.1...1.1.0

1.0.1

• Add client.Transcripts.GetRedactedAudioFileAsync

Full Changelog: 1.0.0...1.0.1

1.0.0

What's Changed

The AssemblyAI C# .NET SDK is now version 1.0.0 and is generally available. Use the SDK to

• transcribe audio via URL or local files
• transcribe streaming audio in real time
• use our audio intelligence models
• apply LLMs to your audio using LeMUR