Speko Docs

voices

GET /v1/voices — read-only catalog of TTS voices grouped by provider.

Browse the curated voice catalog before calling synthesize. Handy for picking a voice id without reading every TTS provider's API docs.

const { voices, providers } = await speko.voices.list();

Signature

speko.voices.list(params?: VoicesListParams): Promise<VoicesListResult>

Parameters

params.provider: string?

Filter to a single provider's voices. Accepts either the routing key (cartesia, xai, alibaba, openai, inworld, elevenlabs) or the catalog suffix form (xai-tts, alibaba-tts, openai-tts).

Returns

VoicesListResult

FieldTypeDescription
voicesVoiceCatalogEntry[]Curated voice roster across the included providers.
providersVoicesProviderEntry[]TTS providers Speko routes to, with their model lists.

VoiceCatalogEntry

FieldTypeDescription
vendorstringRouting-key vendor (matches allowedProviders.tts entries).
idstringVoice id forwarded verbatim to the provider's TTS API.
namestringHuman-readable label, e.g. "Katie (American female)".
modelsstring[]Optional. The models whose voice list includes this voice. Present only where a vendor's models list different voices (Paxa); absent means every model speaks it.

VoicesProviderEntry

FieldTypeDescription
keystringCatalog key, e.g. cartesia, elevenlabs, alibaba-tts.
namestringHuman-readable provider name.
modelsstring[]Models available for the model field on synthesize.
voicesFetchedLivebooleantrue when the provider's voice library is account-scoped (currently only ElevenLabs).

ElevenLabs

ElevenLabs voices are not included in voices; the corresponding providers entry sets voicesFetchedLive: true. Find them in the voice index instead, which works on a Speko-managed key with no ElevenLabs account of your own:

curl "https://api.speko.ai/v1/tts/voices?vendor=elevenlabs&language=es&gender=male" \
  -H "Authorization: Bearer $SPEKO_API_KEY"

Each result's use_with gives the provider, model and voice to pass to synthesize. In MCP, the same search is the voices.search tool.

Example: pick a voice and synthesize

const { voices } = await speko.voices.list({ provider: 'cartesia' });
const sonia = voices.find((v) => v.name.startsWith('Sonia')) ?? voices[0]!;

await speko.synthesize('Hello world', {
  language: 'en',
  voice: sonia.id,
  constraints: { allowedProviders: { tts: ['cartesia'] } },
});

On this page