text
string
required
curl -X POST "https://mvp.tryunsora.com/api/v1/voiceovers/create" \
-H "Authorization: Bearer uns_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Welcome back to the channel. <#0.5#> Today we are breaking down the three biggest AI stories of the week.",
"voice_id": "George",
"stability": 0.5
}'
{
"success": true,
"generation": {
"id": "<string>",
"status": "<string>"
},
"creditsDeducted": 123,
"creditsRemaining": 123
}{
"error": "<string>",
"success": true,
"code": "<string>",
"message": "<string>"
}{
"error": "<string>",
"success": true,
"code": "<string>",
"message": "<string>"
}{
"error": "<string>",
"success": true,
"code": "<string>",
"message": "<string>"
}{
"error": "<string>",
"success": true,
"code": "<string>",
"message": "<string>"
}Voiceover
Create voiceover
Turn a script into speech with an Eleven v3 voice, a MiniMax preset voice or your own cloned voice, then poll until the audio is ready.
POST
/
voiceovers
/
create
curl -X POST "https://mvp.tryunsora.com/api/v1/voiceovers/create" \
-H "Authorization: Bearer uns_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Welcome back to the channel. <#0.5#> Today we are breaking down the three biggest AI stories of the week.",
"voice_id": "George",
"stability": 0.5
}'
{
"success": true,
"generation": {
"id": "<string>",
"status": "<string>"
},
"creditsDeducted": 123,
"creditsRemaining": 123
}{
"error": "<string>",
"success": true,
"code": "<string>",
"message": "<string>"
}{
"error": "<string>",
"success": true,
"code": "<string>",
"message": "<string>"
}{
"error": "<string>",
"success": true,
"code": "<string>",
"message": "<string>"
}{
"error": "<string>",
"success": true,
"code": "<string>",
"message": "<string>"
}Converts a script into speech. The voice you pick decides the model: one of 20 ElevenLabs Eleven v3 voices, one of 12 MiniMax preset voices, or one of your cloned voices. Credits are deducted when the job is queued. Poll Poll voiceover status with the returned
generation.id until status is COMPLETED or FAILED.
Pick a voice first. List voices has the Eleven v3 voices with preview clips; List voices you can use adds the MiniMax presets and your clones.
Headers
| Header | Required | Description |
|---|---|---|
Authorization | Yes | Bearer uns_* API key or Clerk JWT |
Idempotency-Key | No | Max 128 chars. Replays the same response for 24h on API key requests |
Content-Type | Yes | application/json |
Request body
Script to convert to speech. Max 10,000 characters. Use
<#x#> between
words to insert a pause of x seconds (0.01–99.99), e.g. Hello <#1.5#> world.Voice to use:
- Eleven v3:
Aria,Roger,Sarah,Laura,Charlie,George,Callum,River,Liam,Charlotte,Alice,Matilda,Will,Jessica,Eric,Chris,Brian,Daniel,Lily,Bill - MiniMax presets:
Friendly_Person,Wise_Woman,Deep_Voice_Man,Calm_Woman,Casual_Guy,Lively_Girl,Inspirational_girl,Determined_Man,Lovely_Girl,Elegant_Man,English_CaptivatingStoryteller,English_ConfidentWoman - Your clones: the clone
idfrom List voices you can use
Delivery for MiniMax preset voices:
happy, sad, angry, fearful, disgusted, surprised or neutral. Default: neutral. Eleven v3 voices ignore it.Eleven v3 voices only,
0–1. Higher values give a more consistent delivery; lower values are more expressive. Left out, the provider’s default applies. Other voices ignore it.Eleven v3 voices only,
0–1. How closely the output sticks to the base voice; very high values can cause artifacts. Left out, the provider’s default applies. Other voices ignore it.Credits
| Voice | Cost |
|---|---|
| Eleven v3 | 6 credits per started 1,000 characters (a 2,300-character script costs 18) |
| MiniMax preset | 1 credit per started 1,000 characters |
| Your cloned voice | 3 credits per started 500 characters, minimum 3 |
Async completion
Poll Poll voiceover status withgeneration.id until status is COMPLETED or FAILED. Webhooks are not supported on the public API.
Response
{
"success": true,
"generation": {
"id": "cm123abc",
"status": "QUEUED"
},
"creditsDeducted": 6,
"creditsRemaining": 94
}
Example
curl -X POST "https://mvp.tryunsora.com/api/v1/voiceovers/create" \
-H "Authorization: Bearer uns_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Welcome back to the channel. <#0.5#> Today we are breaking down the three biggest AI stories of the week.",
"voice_id": "George",
"stability": 0.5
}'
Errors
| HTTP | When |
|---|---|
400 | Missing text or voice_id, an unknown voice, or an invalid emotion, speed, stability, similarity or output_format |
409 | IDEMPOTENCY_CONFLICT: the Idempotency-Key was already used on a different endpoint |
401 | Invalid auth |
402 | Insufficient credits |
404 | User not found |
429 | Rate limit exceeded |
503 | Voiceover generation not configured |
500 | Server error |
Authorizations
Headers
API key requests only. Retrying with the same key within 24 hours replays the first response (with the Idempotent-Replayed: true header) instead of charging again. The body isn't compared; reusing the key on a different endpoint returns 409 IDEMPOTENCY_CONFLICT. Keys over 128 characters are ignored.
Maximum string length:
128Body
application/json
Credits: Eleven v3 voices 6 per started 1,000 characters; MiniMax preset voices 1 per started 1,000 characters; your cloned voices 3 per started 500 characters (minimum 3).
Script to convert to speech (max 10,000 chars). Supports <#x#> tags between words to pause for x seconds (0.01–99.99).
Maximum string length:
10000A voice from GET /voiceovers/voices (20 Eleven v3 voices such as Aria or Roger), a MiniMax preset (Friendly_Person, Wise_Woman, Deep_Voice_Man, Calm_Woman, Casual_Guy, Lively_Girl, Inspirational_girl, Determined_Man, Lovely_Girl, Elegant_Man, English_CaptivatingStoryteller, English_ConfidentWoman), or the id of one of your cloned voices from GET /voice-clones. The voice decides which model runs.