Providers
Hume
Hume Octave text-to-speech through the Speechbase gateway, with expressive voices, voice cloning, and native timestamps on octave-2.
| Prefix | hume |
| Default model | octave-2 |
| Provider key | Connect under Provider Keys |
Route to Hume by prefixing the model with hume/. Octave is built for
expressive, emotionally aware delivery.
Models
| Model | Streaming | Voice cloning | Timestamps | Max input |
|---|---|---|---|---|
octave-2 | Yes | Yes | Native | 5000 |
octave-1 | Yes | — | STT fallback | 5000 |
Usage
curl -X POST https://api.speechbase.ai/v1/audio/speech \
-H "Authorization: Bearer $SPEECHBASE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"mode": "inline",
"model": "hume/octave-2",
"voice": "KORA",
"text": "Hello from Speechbase!",
"output": "mp3"
}' --output hello.mp3voice is a Hume voice name such as KORA, AURA, STELLA, or DACHER.
Voice cloning
octave-2 supports voice cloning. Register a reference as a saved
Voice and address it by voiceId with
mode: "voice".
Provider options
Anything in providerOptions is forwarded to the Hume API unchanged — for
example an acting_instructions description to steer the performance.