0.11.0

What's Changed

• (feat) Introducing a new platform-agnostic, web-based EVIWebAudioPlayer by @zgreathouse in #351
• (feat) Add .willReconnect to core.ReconnectingWebsocketError by @twitchard in #355
• (break) ImproveReconnectingWebSocket implementation to harden error handling and reconnection logic by @zgreathouse in #358
• (feat) Support ws:// protocol by @twitchard in #360
• (break) Don't swallow errors in fetchAccessToken by @twitchard in #364

Full Changelog: 0.10.3...0.11.0

0.10.3

What's Changed

• 🌿 Fern Regeneration -- April 18, 2025 by @fern-api in #342
  • Add strip_headers to TTS streaming JSON apis, as a convenience when you want to play back audio as a single continued audio file vs a series of standalone audio files.

Full Changelog: 0.10.2...0.10.3

0.10.2

What's Changed

• Add params to configure audio stream by @gregorybchris in #337
  • Enhances the getAudioStream helper to support individual settings for echoCancellation, noiseSuppression, and autoGainControl

Full Changelog: 0.10.1...0.10.2

0.10.1

What's Changed

• 🌿 Fern Regeneration -- April 17, 2025 by @fern-api in #336
  • Text-to-Speech (TTS):
    • Add instantMode to TTS requests (PostedTts) to enable ultra-low latency streaming. When enabled, this provides ultra-low latency streaming suitable for real-time applications. Note: Requires a predefined voice, is only available for streaming, and incurs a 10% higher cost.
    • Added snippetId (string) and text (string) fields to the SnippetAudioChunk
  • Empathic Voice (EVI):
    • Refactored and renamed language model related types for improved clarity (e.g., ReturnLanguageModelModelResource is now LanguageModelType, PostedLanguageModelModelProvider is now ModelProviderEnum).
    • (fix) correct the claude-3-7-sonnet entry to claude-3-7-sonnet-latest in types and documentation examples.

Full Changelog: 0.10.0...0.10.1

0.10.0

What's Changed

• 🌿 Fern Regeneration -- April 7, 2025 by @fern-api in #323
  • (break, fix) - Autopagination is now supported across all list API. The following methods now return a core.Page instead of bespoke page types.
    • HumeClient.empathicVoice.chatGroups.listChatGroups
    • HumeClient.empathicVoice.chatGroups.listChatGroupEvents
    • HumeClient.empathicVoice.configs.listConfigs
    • HumeClient.empathicVoice.configs.listConfigVersions
    • HumeClient.empathicVoice.customVoices.listCustomVoices
    • HumeClient.empathicVoice.tools.listToolVersions
    • HumeClient.tts.voices.list

Full Changelog: 0.9.18...0.10.0

0.9.18

What's Changed

• 🌿 Fern Regeneration -- April 5, 2025 by @fern-api in #317
  • This release corresponds to updating our Fern SDK generator from 0.39.7 -> 0.49.7. See changes here. Relevant changes include improved retry logic, more descriptive errors, and improved ecosystem compatibility.

Full Changelog: 0.9.17...0.9.18

0.9.17

What's Changed

• 🌿 Fern Regeneration -- April 2, 2025 by @fern-api in #303
  • Introduce hume.tts.voices.list and hume.tts.voices.delete methods for managing your Voice Library.
• 🌿 Fern Regeneration -- April 2, 2025 by @fern-api in #307
  • (fix) change hume.tts.synthesizeJsonStreaming to yield a new SnippetAudioChunk type. The previous type Snippet caused deserialization errors.
• 🌿 Fern Regeneration -- April 2, 2025 by @fern-api in #309

Full Changelog: 0.9.15...0.9.17

0.9.15

What's Changed

• 🌿 Fern Regeneration -- March 26, 2025 by @fern-api in #298
  • Add support for hume.tts.synthesizeJsonStreaming and hume.tts.synthesizeFileStreaming methods for streaming generated speech
  • ⚠️ (fix) remove audio_format from Snippet type. This field was released unintentionally and wasn't consistently present, leading to deserialization errors.

Full Changelog: 0.9.14...0.9.15

0.9.14

What's Changed

• 🌿 Fern Regeneration -- March 25, 2025 by @fern-api in #296
  • Added .split_utterances to PostedTts, that can be set explicitly to false to disable auto-segmentation of longer utterances.

Full Changelog: 0.9.13...0.9.14

0.9.13

What's Changed

• 🌿 Fern Regeneration -- March 22, 2025 by @fern-api in #293
  • Added speed and trailing_silence to Utterance.

Full Changelog: 0.9.12...0.9.13