Create Custom Voice

June 5, 2026

Table of contents

  1. Request Headers
  2. Request Body
  3. Responses
  4. Model
  5. Examples
  6. Try It

Create a custom voice (also called a user voice) on a Google Flow account. A custom voice is a saved Text-to-Speech (TTS) clip built on top of one of the 30 system voice presets (Achernar, Achird, Algenib, …) with your own dialog text and voicePerformance description.

Once created, the voice can be:

Captcha: required. See Captcha Parameters.

https://api.useapi.net/v1/google-flow/voices

Request Headers 

Authorization: Bearer {API token}
Content-Type: application/json

Request Body 

{
  "email": "[email protected]",
  "voice": "Achernar",
  "dialog": "Hello, this is a test voice.",
  "voicePerformance": "Cheerful, energetic delivery",
  "displayName": "Cheerful Narrator"
}
  • email is required, the Google Flow account to create the voice on.

  • voice is required, one of the 30 system voice presets. The custom voice inherits the timbre of this base voice. Case-sensitive. Valid values:

    Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon,
Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus,
Puck, Pulcherrima, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel,
Vindemiatrix, Zephyr, Zubenelgenubi
  • displayName is required, user-facing label for the voice. Range: 1-200 chars. Shown in GET /voices and used to distinguish multiple voices in your list.
  • dialog is required, the text the voice will say. Range: 1-120 chars. Used as the audio preview sample.
  • voicePerformance is required, short description of delivery style (e.g. “Cheerful, energetic delivery”, “Deep, brooding villain tone”). Range: 1-120 chars.
  • captchaToken, captchaRetry, captchaOrder are optional, mutually exclusive captcha parameters. See Captcha Parameters for details.

Responses

  • 200 OK

    Voice created.

    {
  "voice": "user:12345-email:6a6f...-voice:d990a2f9-...-mid:d55b6d59-...",
  "source": "user",
  "workflowId": "d990a2f9-...",
  "mediaId": "d55b6d59-...",
  "displayName": "Cheerful Narrator",
  "baseVoice": "Achernar",
  "dialog": "Hello, this is a test voice.",
  "voicePerformance": "Cheerful, energetic delivery",
  "audioUrl": "https://flow-content.google/audio/d55b6d59-...?Expires=...&KeyName=labs-flow-prod-cdn-key&Signature=..."
}

    Use the voice field as the value for referenceAudio_1..referenceAudio_5 on POST /videos, or as the voice body param when creating a character via POST /characters. It’s also the path segment for GET /voices/ref and DELETE /voices/ref.

  • 400 Bad Request

    Validation error (missing required field, invalid voice name, dialog/voicePerformance > 120 chars, etc).

    {
  "error": "Parameter voice is required (must be one of Achernar,Achird,Algenib,…)"
}

  • 401 Unauthorized

    Invalid API token.

    { "error": "Unauthorized" }

  • 404 Not Found

    Account not configured.

    { "error": "Google Flow account [email protected] not found" }

Model 

{
  voice: string                // reference-id used in subsequent calls
  source: 'user'
  workflowId: string
  mediaId: string
  displayName: string
  baseVoice: string            // one of the 30 system voice presets
  dialog: string
  voicePerformance: string
  audioUrl?: string            // signed playback URL (~6h TTL); occasionally absent on transient resolution failure
}

Examples 

  • curl -X POST \
     -H "Authorization: Bearer YOUR_API_TOKEN" \
     -H "Content-Type: application/json" \
     -d '{
       "email": "[email protected]",
       "voice": "Achernar",
       "dialog": "Welcome to the demo.",
       "voicePerformance": "Cheerful, energetic delivery",
       "displayName": "Cheerful Narrator"
     }' \
     "https://api.useapi.net/v1/google-flow/voices"

  • const response = await fetch('https://api.useapi.net/v1/google-flow/voices', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${token}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    email: '[email protected]',
    voice: 'Achernar',
    dialog: 'Welcome to the demo.',
    voicePerformance: 'Cheerful, energetic delivery',
    displayName: 'Cheerful Narrator'
  })
})
const result = await response.json()
console.log('voice ref:', result.voice)

  • import requests
r = requests.post(
    'https://api.useapi.net/v1/google-flow/voices',
    headers={'Authorization': f'Bearer {token}'},
    json={
        'email': '[email protected]',
        'voice': 'Achernar',
        'dialog': 'Welcome to the demo.',
        'voicePerformance': 'Cheerful, energetic delivery',
        'displayName': 'Cheerful Narrator',
    },
)
print('voice ref:', r.json()['voice'])

Try It