Docs
Log inStart free
API referenceVoices

Take to voice

Listen to a recorded take (words and timings, sounds, mood), write it as Drama 3 expression tags and pauses, and speak it in a chosen voice.

Asynchronous: 202 with an id; poll GET /voices/perform/{performanceId}. dry_run quotes. Pacing, pauses, sighs and mood survive; singing and real laughs do not. Credits: listening per second of take, plus the voice; refunded on failure.

POST
/voices/perform

Authorization

bearerAuth
AuthorizationBearer <token>

Typecut API key. Generate one in app.typecut.ai → Settings → API keys. Send as Authorization: Bearer tc_live_….

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

Response Body

application/json

application/json

application/json

application/json

application/json

application/json

application/json

curl -X POST "https://example.com/voices/perform" \  -H "Content-Type: application/json" \  -d '{    "take_media_id": "a759d237-fa20-44d2-bcbe-d7cb1f7939b7"  }'
{
  "data": {
    "dry_run": true,
    "quote": {
      "listen_credits": 0,
      "speak_credits_estimate": 0,
      "total_credits_estimate": 0,
      "take_sec": 0,
      "steps": [
        "string"
      ]
    }
  }
}
{
  "data": {
    "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
    "status": "queued",
    "step_label": "string",
    "heard": [
      {
        "start": 0,
        "end": 0,
        "text": "string"
      }
    ],
    "text_with_tags": "string",
    "tags_fallback": true,
    "note": "string",
    "url": "string",
    "asset_id": "b4695157-0d1d-4da0-8f9e-5c53149389e4",
    "duration_sec": 0,
    "credits": 0,
    "error": "string",
    "next": "string"
  }
}
{
  "error": {
    "type": "string",
    "code": "string",
    "message": "string"
  }
}
{
  "error": {
    "type": "string",
    "code": "string",
    "message": "string"
  }
}
{
  "error": {
    "type": "string",
    "code": "string",
    "message": "string"
  }
}
{
  "error": {
    "type": "string",
    "code": "string",
    "message": "string"
  }
}
{
  "error": {
    "type": "string",
    "code": "string",
    "message": "string"
  }
}

Get a voice clone GET

The state of a voice clone: processing, ready (with tts_preset_id to narrate with) or rejected (with reject_reason), and the intake measures.

Get a take-to-voice run GET

Where a run is: queued, listening, writing, speaking, ready (url, text_with_tags, heard) or failed (error; credits refunded).