ComfyUI Node
OpenAI Text-to-Speech
A ComfyUI node in audio/generation with 7 inputs and 1 output.
OpenAI Text-to-Speech
- audio
◄text►
◄model▾►
◄voice▾►
◄response_format▾►
◄speed1.00►
◄api_key►
◄instructions►
Categoryaudio/generation
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| text | STRING | — | |
| model | COMBO | 3 options: gpt-4o-mini-tts, tts-1, tts-1-hd | |
| voice | COMBO | 9 options: alloy, ash, coral, echo, fable, onyx, +3 | |
| response_format | COMBO | 6 options: mp3, opus, aac, flac, wav, pcm | |
| speed | FLOAT | 1.000.25–4 | — |
| api_key | STRING | Directly put OpenAI API key or .env variable name (OPENAI_API_KEY) | |
| instructionsopt | STRING | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |