Providers
Resemble
Open-source Resemble AI text-to-speech through the Speechbase gateway, with voice cloning and native timestamps.
| Prefix | resemble |
| Default model | default |
| Provider key | Connect under Provider Keys |
Route to Resemble by prefixing the model with resemble/. It's an open-source
model with streaming, voice cloning, and native
timestamps.
Models
| Model | Streaming | Voice cloning | Timestamps | Open source | Languages |
|---|---|---|---|---|---|
default | Yes | Yes | Native | Yes | 23 |
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": "resemble/default",
"voice": "default",
"text": "Hello from Speechbase!",
"output": "mp3"
}' --output hello.mp3Replace voice with a Resemble voice ID, or register a cloned voice as a saved
Voice and address it by voiceId.
Voice cloning
Resemble supports voice cloning from a reference sample. Clone into a saved
Voice, then use mode: "voice" — inline
requests take a plain voice string only.
Provider options
Anything in providerOptions is forwarded to the Resemble API unchanged.