Post-Cutoff.com
  1. Home
  2. Models
  3. Hume Octave 2 (TTS)

Hume Octave 2 (TTS)

Hume AIcurrentaudio/speechOctave

Select via `version: 2` in the TTS request body (`1` = Octave 1, English/Spanish, ~200 ms). Docs still label Octave 2 '(preview)' as of 2026-09-29. Auth header X-Hume-Api-Key. Max 5,000 chars per utterance, 1,000-char descriptions. Formats MP3/WAV/PCM. No Octave 3 announced on Hume's blog through Sept 2026. Speech-to-speech sibling: see hume-evi.

Input
text, audio
Output
audio
License
proprietary
Pricing
per 1k characters: $0.15 (per 1K characters overage on Free/Starter/Creator plans; $0.12 Pro, $0.10 Scale, $0.05 Business (plans include monthly character quotas)) source
Verified
2026-09-29

How to call it

ProviderModel idEndpoint / URLDocs
Hume APIversion: 2https://api.hume.ai/v0/ttsdocs
Web app—platform.hume.ai—

Notable capabilities (3)

Emotionally expressive TTS from Hume AI (Octave = "Omni-capable text and voice engine").

curl https://api.hume.ai/v0/tts -H "X-Hume-Api-Key: $HUME_API_KEY" -H "Content-Type: application/json" \
  -d '{"version":2,"utterances":[{"text":"I cannot believe it worked!","description":"a delighted, breathless scientist"}]}'

Sources: https://dev.hume.ai/reference/text-to-speech-tts/synthesize-json , https://www.hume.ai/pricing , https://www.hume.ai/blog/octave-2-launch

Other Hume AI models

Hume EVI 3 / EVI 4 mini (speech-to-speech)