0.9.12

Introducing Octave TTS

This release includes support for Hume AI's Octave TTS API. Learn more on our docs page, or try it out on the web at hume.ai.

Unlike conventional TTS that merely "reads" words, Octave is a speech-language model that understands what words mean in context, unlocking a new level of expressiveness. It acts out characters, generates voices from prompts, and takes instructions to modify the emotion and style of a given utterance.

What's Changed

• 🌿 Fern Regeneration -- February 26, 2025 by @fern-api in #276
  • Introducing hume.tts client.
• 🌿 Fern Regeneration -- February 26, 2025 by @fern-api in #278
  • (fix) improved return type for hume.tts.synthesizeFile.

Full Changelog: 0.9.10...0.9.12

0.9.10

What's Changed

• 🌿 Fern Regeneration -- January 15, 2025 by @fern-api in #254
  • Add WebhookEvent payload types.

Full Changelog: 0.9.9...0.9.10

0.9.9

What's Changed

• (fix) Add custom voices by @twitchard in #250
• Make Content-Type optional in convertBase64ToBlob by @twitchard in #251
• 🌿 Fern Regeneration -- January 13, 2025 by @fern-api in #253
  • Add support for .webhooks to the Config resource
  • Add support for .configId filter to the .empathicVoice.chats.listChats(...) method
  • Add support for .mostRecentConfig to the ChatGroup resource.

Full Changelog: 0.9.8...0.9.9

0.9.8

What's Changed

• Ensures query params are not appended if they don't contain data by @zachkrall in #242

Full Changelog: 0.9.7...0.9.8

0.9.7

What's Changed

• 🌿 Fern Regeneration -- December 4, 2024 by @fern-api in #241
  • ⚠️ (break) Updated voice parameters: removed articulation
  • Improved type of SessionSettings.variables

Full Changelog: 0.9.6...0.9.7

0.9.6

What's Changed

• 🌿 Fern Regeneration -- November 6, 2024 by @fern-api in #226
  • Adds interim field to UserMessage events in EVI chats, to indicate whether a user message is "interim".
  • Adds enum members for Claude Haiku 3.5.
• Adds the verbose_transcription query param to the /chat endpoint, which enables the sending of interim messages by @twitchard in #227

Full Changelog: 0.9.4...0.9.6

0.9.4

What's Changed

• 🌿 Fern Regeneration -- October 31, 2024 by @fern-api in #221
  • (fix) added CUSTOM_VOICE as a member to the ReturnVoice.voice_provider enum
  • (fix) added correct return types for the audio reconstruction endpoints
  • (feat) Typed .language_model.model_resource on POST /v0/evi/configs as an enum instead of a string.

Full Changelog: 0.9.3...0.9.4

0.9.3

What's Changed

• 🌿 Fern Regeneration -- October 24, 2024 by @fern-api in #208
  • Add support for hume.empathicVoice.chats.getAudio(...) for getting a URL that you can use to download the reconstructed audio for a chat
    • Note: this method will not return a ready-to-use URL right away, it will kick off a job to ready the URL. You can use this like

      let json = await hume.empathicVoice.chats.getAudio(...);
      await new Promise((resolve) => setTimeout(() => resolve(), 10000))
      json = await hume.empathicVoice.chats.getAudio(...);
      if (json.status !== 'COMPLETE') {
        throw new Error('Job did not complete in 10 seconds')
      }
      const urlContainingDownload = json.signed_audio_url;     

  • Add support for hume.empathicVoice.chatGroups.getAudio(...) to list urls containing reconstructed audio for many chats in a chat group
  • Custom Voices
    • Add support for new base voice SUNNY
    • Updates custom voice parameters to reflect the latest parameters.

Full Changelog: 0.9.2...0.9.3

0.9.2

What's Changed

• (feat): [types] require credentials when initializing HumeClient by @twitchard in #190
• Configures prettier to ignore .mock directory by @twitchard in #191
• fix: expose getter on Socket.ts by @fern-bot in #200

Full Changelog: 0.9.1...0.9.2

0.9.1

What's Changed

• (fix) Prevent unwanted deserialization errors for null ReturnVoice.custom_voice (PR)

Full Changelog: 0.9.0...0.9.1