Text-to-Speech
Convert text to an audio file using OpenAI's text-to-speech models.
Converts text to natural-sounding speech using OpenAI's advanced text-to-speech models, facilitating accessibility and multimedia applications.
Text-to-Speech
Text*Text
InstructionText
ModelSelect
VoiceSelect
Inputs
Each input can be typed in directly or connected to another node's output.
| Input | Type | Required | Description | Available when |
|---|---|---|---|---|
| Text | Text | Required | Enter your text here | — |
| Instruction | Text | Optional | Prompt the model to control aspects of speech (accent, emotional range, intonation, speed, tone, ...) | Model is “gpt-4o-mini-tts” |
Settings
| Setting | Type | Default | Description |
|---|---|---|---|
| Model | Select | gpt-4o-mini-tts | |
| Voice | Select | alloy |
Model options
| Option | Default |
|---|---|
| gpt-4o-mini-tts | ✓ |
| tts-1 | |
| tts-1-hd |
Voice options
| Option | Default |
|---|---|
| alloy | ✓ |
| ash | |
| ballad | |
| coral | |
| echo | |
| fable | |
| onyx | |
| nova | |
| sage | |
| shimmer |
Output
Type: Audio (audioUrl)