Get Started

Voices & Models

Onepin runs voice workflows across 100+ TTS models from leading text-to-speech providers.

Onepin is a voice workflow platform that orchestrates, validates, and ships production-ready audio across 100+ TTS models. A single workflow can route different steps to different models, so you are never locked to one vendor.

How many TTS models does Onepin support?

Onepin runs across 100+ text-to-speech (TTS) models spanning multiple providers. New models are added continuously, and a workflow can mix models from different providers in the same pipeline.

The exact set available to you depends on your workspace and plan. The live, authoritative catalog is always returned by the API and CLI — see Browse the catalog below.

Which TTS providers does Onepin integrate?

Onepin integrates leading commercial and specialist TTS providers, including:

ProviderExample models
ElevenLabseleven_multilingual_v2, eleven_turbo_v2
Cartesiasonic-2
Naverclara
Respeecherreal_time
Rimearcana
…and moreNew providers and models are onboarded regularly

This table shows representative models, not the full list. Each provider exposes multiple voices and, in several cases, multiple models — together totalling 100+ TTS models across the platform.

How do I browse the available voices and models?

The catalog returned by your workspace is the source of truth. List it from the CLI or the API:

$# CLI — every voice available to your workspace, with provider and locale
$onepin voices list --all --json | jq '.[] | {id, display_name, provider, locale}'
$
$# Filter by locale (BCP-47)
$onepin voices list --locale en-us
1from onepin import OnePinClient
2
3client = OnePinClient(token="op_live_...")
4for v in client.voices.list(limit=50):
5    print(v.id, v.display_name, v.locale)

The API Reference and SDK enumerate the currently exposed model identifiers — a subset of the full provider catalog, not the platform ceiling. Use onepin voices list for the complete, up-to-date set your workspace can use.