Skip to content

Releases: HumeAI/hume-python-sdk

v0.7.11

26 Mar 16:48
c1cf1a8
Compare
Choose a tag to compare

What's Changed

  • 🌿 Fern Regeneration -- March 26, 2025 by @fern-api in #251
    • Add support for hume.tts.synthesize_json_streaming and hume.tts.synthesize_file_streaming 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: v0.7.10...v0.7.11

v0.7.10

25 Mar 23:11
32bee13
Compare
Choose a tag to compare

What's Changed

  • 🌿 Fern Regeneration -- March 25, 2025 by @fern-api in #248
    • Added .split_utterances to PostedTts, that can be set explicitly to false to disable auto-segmentation of longer utterances.

Full Changelog: v0.7.9...v0.7.10

v0.7.9

22 Mar 02:23
1f0357a
Compare
Choose a tag to compare

What's Changed

  • 🌿 Fern Regeneration -- March 22, 2025 by @fern-api in #247
    • Add speed and trailing_silence to Utterance

Full Changelog: v0.7.8...v0.7.9

v0.7.8

26 Feb 12:48
1163822
Compare
Choose a tag to compare

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 #236
    • Introduce AsyncHumeClient.tts client for Octave.
    • (fix, breaking) Renamed method create_prompt_verison to create_prompt_version.

Full Changelog: v0.7.7...v0.7.8

v0.7.7

15 Jan 21:56
270694e
Compare
Choose a tag to compare

What's Changed

  • 🌿 Fern Regeneration -- January 15, 2025 by @fern-api in #222
    • Add WebhookEvent payload types.
  • 🌿 Fern Regeneration -- January 15, 2025 by @fern-api in #224
    • Updates to latest fern generator.
    • HttpClient now takes callables for base_headers, base_timeout, and base_url instead of hardcoded values

Full Changelog: v0.7.6...v0.7.7

v0.7.6

13 Jan 23:38
5acfaf4
Compare
Choose a tag to compare

What's Changed

  • 🌿 Fern Regeneration -- January 13, 2025 by @fern-api in #220
    • Add support for .webhooks to the Config resource
    • Add support for .config_id filter to the .empathic_voice.chats.listChats(...) method
    • Add support for .most_recent_config to the ChatGroup resource.

Full Changelog: v0.7.5...v0.7.6

v0.7.5

04 Dec 00:33
730518e
Compare
Choose a tag to compare

What's Changed

  • 🌿 Fern Regeneration -- November 6, 2024 by @fern-api in #211
    • 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.
  • 🌿 Fern Regeneration -- December 4, 2024 by @fern-api in #217
    • ⚠️ (break) Updated voice parameters: removed articulation
    • Improved type of SessionSettings.variables

Full Changelog: v0.7.4...v0.7.5

v0.7.4

31 Oct 17:07
fa82ef9
Compare
Choose a tag to compare

What's Changed

  • 🌿 Fern Regeneration -- October 31, 2024 by @fern-api in #210
    • (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: v0.7.3...v0.7.4

v0.7.3

24 Oct 20:31
ca23cd2
Compare
Choose a tag to compare

What's Changed

  • 🌿 Fern Regeneration -- October 24, 2024 by @fern-api in #203

What's Changed

  • Add support for hume.empathic_voice.chats.get_audio(...) 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
      result = await hume.empathic_voice.chats.get_audio(...)
      await asyncio.sleep(10)
      result = await hume.empathic_voice.chats.get_audio(...)
      if result.status != "COMPLETE":
        raise TimeoutError('Job did not complete in 10 seconds')
      url_containing_download = json.signed_audio_url 
  • Add support for hume.empathic_voice.chat_groups.get_audio(...) 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: v0.7.2...v0.7.3

hume 0.7.2

02 Oct 17:46
935ed6a
Compare
Choose a tag to compare

This release fixes a validation error in ReturnConfig when creating a config with a null custom_voice. Previously, this would raise a pydantic ValidationError. Now, null values for custom_voice are properly handled.

Example of fixed usage:

client = AsyncHumeClient(api_key=<HUME_API_KEY>) # replace <HUME_API_KEY> with your API key
resp = await client.empathic_voice.configs.create_config(name="test", evi_version=1)
# This now works without raising a ValidationError, even if custom_voice is implicitly None