ComfyUI Node
Seed Audio 1.0 · Text to Audio
Multi-voice audio scenes with music and effects 54 credits ($0.54) per run. Model: bytedance/seed-audio-1.0/text-to-audio Fields, prices and examples: https://popnow.ai/docs/models/seed-audio-1-0
Seed Audio 1.0 · Text to Audio
- reference_audio_urls
- image_url
- audio
- task id
◄prompt►
◄speed1.00►
◄pitch0►
◄volume1.00►
◄output_formatmp3►
◄sample_ratemodel default►
CategoryPopNow/Audio/ByteDance
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Describe the whole audio scene: who speaks, how, what they say (in quotes), and any music, ambience or sound effects. | |
| speed | FLOAT | 1.000.5–2 | Speech rate multiplier; 1 is normal. |
| pitch | INT | 0-12–12 | Pitch shift in semitones; 0 keeps the original pitch. |
| volume | FLOAT | 1.000.5–2 | Loudness multiplier; 1 is the normal level. |
| output_format | COMBO | mp3 | File format of the result; pcm is headerless 16-bit little-endian stereo samples. |
| sample_rate | COMBO | model default | Sample rate in Hz. The model uses 24000 when omitted. |
| reference_audio_urlsopt | COMFY_AUTOGROW_V3 | Up to three reference clips, called @Audio1 to @Audio3 in the prompt. Not with image_url. | |
| image_urlopt | IMAGE | Optional reference image to build the audio around. Not with reference_audio_urls. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | Several results come back as a batch; Save Audio writes one file each. |
| task id | STRING | The PopNow task id, for the API console logs or support. |