v0.13.4

What's Changed

• add allow_connection override to async by @ivaaan in #418
• 🌿 Fern Regeneration -- November 7, 2025 by @fern-api[bot] in #419

Full Changelog: v0.13.3...v0.13.4

v0.13.3

What's Changed

• Add allow_connection query param to chat connect by @twitchard in #415

Full Changelog: v0.13.2...v0.13.3

v0.13.2

What's Changed

• Support for Control Plane API
• Support for Voice Conversion
• Fix for flattening session settings query params: #406

Full Changelog: v0.13.1...v0.13.2

v0.13.1

What's Changed

• v0.13.0 backward compatibility by @ivaaan in #402
  • Restores as deprecated several methods and classes related to .connect_with_callbacks that was removed from the EVI client in v0.13.0
• Move ChatConnectOptions to socket_client for backward compatibility by @ivaaan in #404

New Contributors

• @ivaaan made their first contribution in #402

Full Changelog: v0.13.0...v0.13.1

v0.13.0

What's Changed

• Fern upgrade by @twitchard in #401
  • (feat) added support for hume_client.empathic_voice.stream_input.connect(...) for supplying streaming input to TTS
  • (break) removed base_url as an argument to HumeClient / AsyncHumeClient. Please use environment instead.
  • Various changes to imports, type names, package versions, and infrastructure related to the upgrade of our SDK generator from fern.
    Full Changelog: v0.12.1...v0.13.0

v0.12.1

What's Changed

• Add support for session_settings when connecting to an EVI chat #382
• 🌿 Fern Regeneration -- October 1, 2025 by @fern-api[bot] in #384

Full Changelog: v0.12.0...v0.12.1

v0.12.0

What's Changed

This is a significant release, corresponding to the release of our new multilingual Text-to-Speech model, Octave 2 (preview), and our multilingual-capable EVI version, 4-mini. See the announcement.

• #374, #380
  • TTS: version="2" is now supported in all TTS requests. Octave 2 (preview) has multilingual capabilities, however does not currently support the description field. If you require acting instructions or voice design, please continue to use Octave 1. Voices saved with Octave 1 are forwards-compatible with Octave 2 -- however voices saved using Octave 2 are not backwards-compatible with Octave 1.
  • TTS: Word-level and phoneme-level timestamps are now available for TTS created using Octave 2. This enables use cases such as word highlighting or lip-syncing. Pass version="2", include_timestamp_types=['word', 'phoneme'] into synthesizeJsonStreaming to receive timestamp messages, or access the .timestamps field on Snippet.
  • (break) The type of messages yielded by synthesizeJsonStreaming has changed from SnippetAudioChunk to TtsOutput (= Union[SnippetAudioChunk,TimestampMessage])
    • EVI: version 4-mini is now supported. Configs using 4-mini must specify a supplemental LLM and cannot enable quick responses.
  • EVI: new supplemental LLMs: claude-sonnet-4-5-20250929 and grok-4-fast-non-reasoning-latest

Full Changelog: v0.11.7...v0.12.0

v0.11.7

What's Changed

• 🌿 Fern Regeneration -- September 26, 2025 by @fern-api[bot] in #371
  • Adds version field to TTS requests

Full Changelog: v0.11.6...v0.11.7

v0.11.6

What's Changed

• fix: play_audio_streaming termination by @twitchard in #366

Full Changelog: v0.11.5...v0.11.6

v0.11.5

What's Changed

• #365: Fern Generation (@app/fern-api)
  • Add voice_id to session_settings. You can now change voices within an EVI chat!
  • Add request_id field to SnippetAudioChunk to aid in debugging.

Full Changelog: v0.11.4...v0.11.5