Amazon Polly Neural API
Turn text into natural-sounding speech. Useful for straightforward narration, explainers and news-style voiceovers.
Amazon · polly-neural
Text to speech
Turn text into natural-sounding speech. Useful for straightforward narration, explainers and news-style voiceovers.
Put a prompt and "model": "polly-neural" on an audio clip, and the render generates it and edits it into the video. To generate it on its own, send the same asset to the generate endpoint.
Built forStraightforward narration · Explainers · News-style reads
Technical specifications
| Input | Script text |
|---|---|
| Output | Speech |
| Length | Follows the script |
| Voices | Choose a voice by name |
| Style | Optional newscaster style |
{
"asset": {
"type": "audio",
"prompt": "Here's today's weather for Sydney: sunny, with a top of twenty-four.",
"model": "polly-neural",
"options": {
"voice": "Joanna"
}
}
}Pricing
Generation is paid in credits from the same balance as rendering, at what the model's provider charges plus a small margin. See AI generation pricing.
| Mode | Charged per | Price changes with | Length a quote assumes without one |
|---|---|---|---|
| Text to speech | Character of the prompt, minimum 100 | Fixed rate | — |
Get a quote
POST /generate/quote takes the same body as the generate endpoint and returns what that generation would cost. Nothing is generated, reserved or charged.
curl -X POST \
-H "Content-Type: application/json" \
-H "x-api-key: $SHOTSTACK_API_KEY" \
-d '{
"asset": {
"type": "audio",
"prompt": "Here'\''s today'\''s weather for Sydney: sunny, with a top of twenty-four.",
"model": "polly-neural",
"options": {
"voice": "Joanna"
}
}
}' \
https://api.shotstack.io/edit/stage/generate/quoteThe response gives credits, the price of that request, and ceiling, which is true when the request has no length for a model charged by length, so the price is an estimate. Prices follow the providers, so ask again rather than storing one.
How it compares
Amazon Polly Neural beside the other models in Shotstack that make the same thing.
| Model | Best for | Voices | Languages | Extra controls | Charged per |
|---|---|---|---|---|---|
| Amazon Polly Neural | Straightforward narration and news-style reads | Polly voices by name | — | newscaster style | Character of the prompt, minimum 100 |
| ElevenLabs Multilingual v2 | Consistent narration and localisation | 21 | 29 | stability, similarity, style | Character of the prompt |
| ElevenLabs Turbo v2.5 | Low-latency speech | 21 | 32 | stability, similarity, style | Character of the prompt |
| MiniMax Speech 2.8 HD | A choice of voices across many languages | 17 | 38 | — | Character of the prompt |