Create Voiceover
Generate expressive, natural-sounding speech from text with the ElevenLabs v3 model.
Direct the performance with inline audio tags in square brackets, such as [excited],
[whispers], [laughs] or [pause 1s]: the model performs them instead of reading them aloud.
Up to 5,000 characters per request.
Credits: charged per started block of 10 characters of text.
The request is processed asynchronously: the endpoint returns a task_id
immediately. Retrieve the result by polling
GET /v1/ai/voiceover/elevenlabs-v3/{task-id} or by providing an optional webhook_url.
Authorizations
Your Magnific API key. Required for authentication. Learn how to obtain an API key
Body
The text to convert to speech, up to 5,000 characters. Supports UTF-8 characters including accented letters and non-Latin scripts.
Inline audio tags in square brackets direct the performance instead of being read aloud, e.g. [excited], [whispers], [laughs] or [pause 1s].
1 - 5000"[excited] Welcome to Magnific! [pause 0.5s] Let's create something amazing."
The unique identifier of the ElevenLabs voice to use for synthesis. You can find voice IDs in the ElevenLabs voice library.
1 - 255^[a-zA-Z0-9_-]+$"21m00Tcm4TlvDq8ikWAM"
Controls how closely the delivery sticks to the voice versus how freely it performs the text: 0.0 (Creative) is the most expressive and follows audio tags most strongly, 0.5 (Natural) is balanced, 1.0 (Robust) is the most consistent.
0 <= x <= 10.5
Controls how closely the generated voice matches the original voice. Higher values produce closer matching.
0 <= x <= 10.75
Optional callback URL that will receive asynchronous notifications whenever the task changes status. The payload sent to this URL is the same as the corresponding GET endpoint response, but without the data field.
"https://www.example.com/webhook"
Response
OK - Task created successfully