Speech from Text

The Speech from Text card converts written text into spoken audio using ElevenLabs. You can use an existing voice, design a new one from a description, or clone a voice from an audio sample.

Note

All generation endpoints require the agent_id query parameter.

Voice methods

Use canonical generation_type: "speech_from_text" for all speech generation. Choose the voice path with data.voice_method.

Method	data.voice_method	Description
My Voices	my_voices	Use an existing saved voice by ID.
Design Voice	design_voice	Create a new voice from a text description.
Clone Voice	clone_voice	Clone a voice from an audio sample.

---

My Voices

Use an existing ElevenLabs voice to generate speech.

POST /v1/autocontentengine/{id}/cells/{cell_id}/generate?agent_id={agent_id}

Request body

Field	Type	Required	Description
generation_type	string	Yes	"speech_from_text".
data.script	string	Yes	The text to convert to speech.
data.voice_method	string	Yes	"my_voices".
data.voice_id	string	Yes	Saved voice ID.
data.language	string	No	Language code, for example "en".
data.speed	number	No	Playback speed.

Example

curl -X POST "https://api.gen.pro/v1/autocontentengine/101/cells/3000/generate?agent_id=42" \
  -H "X-API-Key: your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "generation_type": "speech_from_text",
    "data": {
      "script": "Welcome back to another episode of our series.",
      "voice_method": "my_voices",
      "voice_id": "pNInz6obpgDQGcFmaJgB"
    }
  }'

---

Design Voice

Create a brand-new voice from a text description and use it to generate speech.

POST /v1/autocontentengine/{id}/cells/{cell_id}/generate?agent_id={agent_id}

Request body

Field	Type	Required	Description
generation_type	string	Yes	"speech_from_text".
data.script	string	Yes	The text to convert to speech.
data.voice_method	string	Yes	"design_voice".
data.name	string	Yes	A name for the new voice.
data.language	string	Yes	Language code (e.g., "en").
data.gender	string	Yes	"male" or "female".
data.voice_prompt	string	Yes	A description of the voice characteristics (e.g., "warm, friendly narrator with a slight British accent").

Example

curl -X POST "https://api.gen.pro/v1/autocontentengine/101/cells/3000/generate?agent_id=42" \
  -H "X-API-Key: your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "generation_type": "speech_from_text",
    "data": {
      "script": "Welcome back to another episode of our series.",
      "voice_method": "design_voice",
      "name": "Friendly Narrator",
      "language": "en",
      "gender": "male",
      "voice_prompt": "warm, friendly narrator with a slight British accent"
    }
  }'

---

Clone Voice

Clone a voice from an audio sample and use the clone to generate speech.

POST /v1/autocontentengine/{id}/cells/{cell_id}/generate?agent_id={agent_id}

Request body

Field	Type	Required	Description
generation_type	string	Yes	"speech_from_text".
data.script	string	Yes	The text to convert to speech.
data.voice_method	string	Yes	"clone_voice".
data.name	string	Yes	A name for the cloned voice.
data.audio_resource_id	string	Yes	Content resource ID for the voice sample.
data.language	string	Yes	Language code (e.g., "en").
data.gender	string	Yes	"male" or "female".

Caution

The voice sample must be at least 30 seconds long for reliable cloning results.

Example

curl -X POST "https://api.gen.pro/v1/autocontentengine/101/cells/3000/generate?agent_id=42" \
  -H "X-API-Key: your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "generation_type": "speech_from_text",
    "data": {
      "script": "Welcome back to another episode of our series.",
      "voice_method": "clone_voice",
      "name": "My Custom Voice",
      "audio_resource_id": "audio_res_123",
      "language": "en",
      "gender": "male"
    }
  }'

---

Additional options

These options can be added to the data object for any voice method:

Field	Type	Default	Description
enhance_voice	boolean	false	Apply post-processing to enhance audio clarity.

---

Response

All voice methods return a generation ID. Poll Check generation status until complete. The finished generation includes the audio URL in output_resources.

{
  "id": 9000,
  "status": "completed",
  "output_resources": [
    {
      "id": 1500,
      "url": "https://cdn.gen.pro/outputs/voiceover-abc123.mp3",
      "object_type": "audio",
      "type": "output"
    }
  ]
}

Tip

You can also run speech generation on a layer within a cell by using the layer endpoint: POST /v1/autocontentengine/{id}/cells/{cell_id}/layers/{layer_id}/generate?agent_id={agent_id}

---

Cell configuration

Tip

Cell configuration is set via PATCH /v1/autocontentengine/{id}/cells/{cell_id} with additional_attributes in the request body. These defaults are used when generation is triggered.

Field	Type	Description
autoGenerate	boolean	Auto-trigger generation when the script cell changes.

Voice method, voice ID, language, and gender are passed in the generation data parameter, not stored as cell attributes.