Realtime TTS-2 is live. Built for realtime conversation that feels human. Read the Realtime TTS-2 announcement

VoiceService

Redeem a voice copy token

Inworld Voice API reference: use a voice copy token to create your own private copy of a custom voice in your workspace.

POST/voices/v1/voices:redeemCopyToken

Copy a custom voice into an allowed destination workspace using a token from Issue a voice copy token. Use the destination workspace's API key with voice write permission (api.dsgnt.voices::rw). You do not need access to the source workspace.

This endpoint accepts workspace-scoped tokens only. Email-based tokens from Portal's Export Voice flow cannot be redeemed here.

Copy the voice

Send the voiceCopyTokenId returned when issuing the token in the request body. Set displayName to name the copy, or omit it to keep the source voice's display name. A blank display name also keeps the source name.

bash
curl --request POST 'https://api.inworld.ai/voices/v1/voices:redeemCopyToken' \
  --header "Authorization: Basic $DESTINATION_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "voiceCopyTokenId":"00000000-0000-4000-8000-000000000001",
    "displayName":"Production narrator"
  }'

The API key's workspace is the destination. Its ID must appear in the token's allowedWorkspaces.

The response is a voice object. An illustrative response, with optional fields omitted:

json
{
  "voiceId": "destination-workspace__production-narrator",
  "displayName": "Production narrator",
  "source": "IVC"
}

Use the returned voiceId in speech synthesis with the destination workspace's API key. The copy is private and independent of the original.

Redemption requirements

  • The token must be less than seven days old and grant access to the destination workspace.
  • The source voice must still exist and be available for copying. A deleted or taken-down source cannot be copied.
  • The destination workspace must have room within its custom-voice limit. Redemption also requires available credits.

Each successful call creates another voice, even when you reuse the same token. Keep the returned voice ID so you can use the copy without redeeming again.

Authorizations

Authorizationstringrequired

Your API key. Read permissions are required for GET endpoints. Write permissions are required for POST, PATCH, and DELETE endpoints.

For Basic authentication, please populate Basic $INWORLD_API_KEY. You can create a key in one command with the Inworld CLI: inworld workspace add-key.

Body

application/json

parentstring

Destination workspace in the form workspaces/{workspace}. Omit to use the workspace associated with the API key. The caller needs voice write access to this workspace, which must be on the token allowlist.

voiceCopyTokenIdstringrequired

The voiceCopyTokenId returned when issuing the token. Send this value in the request body.

displayNamestring

Display name for the copied voice. If omitted or blank, the source voice display name is kept.

Response

200 - application/json

voiceIdstring

Voice ID. SYSTEM voices use a simple name (e.g. Alex); IVC voices are workspace-prefixed ({workspace}__{voice}).

langCodeenum<string>

Primary language of the voice in upper-snake format (e.g. EN_US). Note that when filtering via lang_code, you can pass BCP-47 (en-US), underscore form (en_US), or a language prefix (en) — but the response always returns upper-snake.

Available options:EN_USZH_CNKO_KRJA_JPRU_RUAUTOIT_ITES_ESPT_BRDE_DEFR_FRAR_SAPL_PLNL_NLHI_INHE_IL

languageCodestring

Canonical wire form of the voice's primary language as a single string (e.g. en-US, es-MX, vi). Populated on every read alongside the legacy langCode enum. Immutable after creation.

displayNamestring

The human-readable name shown anywhere the voice is listed or selected.

descriptionstring

Longer blurb that explains the voice's tone, accent, use cases, or other relevant attributes.

tagsstring[]

Free-form labels for filtering, grouping, and discovery (e.g. british, calm).

namestring

Resource identifier. Workspace voices use workspaces/{workspace}/voices/{voice}; system and shared voices may use a bare identifier. For synthesis and audio previews, use voiceId unchanged instead of constructing a resource path.

sourceenum<string>

Voice provenance: SYSTEM (Inworld system voice), IVC (instant voice clone), TVD (voice design), PVC (professional or supplied custom voice), or OTHER. Treat provenance separately from community-sharing and ownership metadata.

Available options:SYSTEMIVCTVDPVCOTHER

genderenum<string>

Voice gender (male, female, neutral). Empty string if unspecified. Voices with no gender are excluded when filtering with an explicit gender = predicate.

Available options:malefemaleneutral

ageGroupenum<string>

Age group of the voice (young, middle_aged, elderly). Empty string if unspecified.

Available options:youngmiddle_agedelderly

categoriesenum<string>[]

Use-case categories the voice belongs to. Filterable with the : (has) operator.

Supported values: companions, enterprise, education_training, developer_assistants, healthcare, interactive_media.

promptLanguagesstring[]

Every language the voice can speak, in BCP-47 format (e.g. en-US): its source language first, then each language it has been localized to. A voice without localizations has one entry; a voice whose language is detected automatically has none. Returned by both listing and getting a voice.

ownedboolean

For a community voice result, whether the calling workspace owns the voice. Interpret alongside community-sharing metadata; this field is not a general test for whether synthesis is permitted.