LocalClaw/TTS/OCTAVE 2
Vendor API speech reference

OCTAVE 2

Catalogue summary: Second-gen emotion-aware speech-language model. Generates voice, style and personality from a text description alone - no reference audio required. Rich control over arousal, valence and speaking style. Research-first release.

Repository editorial metadata; verify comparative claims in the linked upstream material.

Vendor API requiredvendor-hosted speech generation7 languagesHume Terms (research)
Compare TTS modelsOpen upstream source
Catalogue quality
9.4/10
Catalogue speed
7.5/10
Model size
3.2 GB
Voices
Prompt-generated voices + style

Can OCTAVE 2 run locally?

OCTAVE 2 does not currently have a verified local checkpoint or runtime in the LocalClaw catalogue. The listed Python package is a client for Hume AI's vendor-hosted API. Use the verified setup options on this page; no terminal command is required to choose the right path.

Hume Terms (research) license. Review upstream restrictions before commercial use.

Upstream source
emotioncontrollablestreamingmultilingual

Audio profile

Cat. quality
9.4
Cat. speed
7.5
Profile
8.8

Best fit

OCTAVE 2 is useful for evaluating Hume AI's hosted expressive speech controls when vendor API use is acceptable.

Hardware: gpuapple

Model details

Type
Vendor API speech reference
Family
octave
Latency
low
Formats
pytorchapi
Languages
en, de, fr, es, it, pt, ja
Context
Describe a speaker in natural language

Access the online service

01
Check service termsReview the upstream service, privacy and usage terms before sending any text.
02
Install clientInstall the client package; this does not download a local inference model.
03
Test onlineConfirm network delivery, data handling, latency and vendor availability.

Good for

  • vendor-hosted speech generation
  • Vendor API required
  • emotion, controllable, streaming

Watch before shipping

  • Validate pronunciation, latency and artifacts with your own voice samples.
  • Review the upstream license and acceptable-use notes.
  • Benchmark on your target CPU, Apple Silicon or GPU setup.

Related TTS and speech models

Zyphra ZONOS2 Local TTS model · Q 9.6 · Speed 8.5 Boson AI Higgs TTS 3 4B Local TTS model · Q 9.7 · Speed 8 OpenBMB VoxCPM2 Local TTS model · Q 9.4 · Speed 8.3 DarkPs ICE-012 Audio Local TTS model · Q 9.1 · Speed 8.2 OpenMOSS / MOSI.AI MOSS-TTS Local TTS model · Q 9.2 · Speed 6.8 Phạm Nguyễn Ngọc Bảo VieNeu-TTS v3 Turbo Local TTS model · Q 9.2 · Speed 9.4 BreezeBlue Breeze TTS 2 Local TTS model · Q 9.6 · Speed 8.4 Qwen Team (Alibaba Cloud) Qwen3-TTS (0.6B / 1.7B) Local TTS model · Q 9.5 · Speed 8.5
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw