Upload And Extend Audio · V5.5
Your file, continued from where you pick
- audio
- url
- all_urls_json
- task_id
- raw_json
- credits_consumed
- credits_left
Here's the difference between this node and its sibling Extend Music, in one line: Extend takes a Suno audio_id, this one takes an upload_url. If your source is a file you already own - a loop you made, a stem, an old render, something from a local model - this is the node, because KIE can fetch a URL and it can't fetch your hard drive.
The job is the same: pick a point in the track and let the model continue from there. Useful when a 20-second generate comes back and you want a 90-second version, or when a locally generated loop needs a middle section before you cut it into a video.
How it works
The pack builds its node classes from KIE's official API documentation on startup, one node per documented model version - so this class is fixed to V5_5 with no dropdown to change. The node builds the documented request body, submits it to KIE's task endpoint (envelope model ai-music-api/upload-and-extend, inner model V5_5), then polls KIE's record-info endpoint every couple of seconds with exponential backoff until the task completes. On success it downloads the mp3 and returns a native ComfyUI AUDIO; on failure it raises with the task id and the provider's message.
The inputs that matter
- upload_url (required) - the source, as a public URL. The docs cap upload-based source audio at 8 minutes and say the source alone is enough to generate.
- prompt - used as lyrics only if
lyricsis empty, and it must not be set wheninstrumentalis true. - continue_at - the field that actually matters. Seconds, default 60, and per the docs it must be greater than 0 and less than the total duration of the uploaded audio. Get this wrong in either direction and the request fails.
- instrumental - defaults to
true, which is worth noticing, because it means a lyrics prompt is ignored unless you flip it. That default is the opposite of the Extend node's.
The rest is steering: style (align it with the source; it's up to 1000 characters on this tier), title, negative_tags, vocal_gender, style_weight, weirdness_constraint, audio_weight, persona_id / persona_model, lyrics, variety (0–4), plus timeout_seconds (1200) and callback_url (leave empty).
Outputs: audio, url, all_urls_json, task_id, raw_json, credits_consumed, credits_left. When you extend an upload, the response carries both source and generated URLs - all_urls_json is where you keep them, and task_id plus url make cheap logging if you're iterating on continue_at.
Feeding it a local file
upload_url is a text box, not an AUDIO socket, so wire it: drop KIE • Upload Audio (in KIE Next/Utility/Media), connect your AUDIO to it, then right-click upload_url on this node, choose Convert widget to input, and connect the URL string. Once that's in place you can run a fully local-generate → upload → extend chain without touching a URL by hand.
Installing
ComfyUI Manager, search "KIE Nodes Next"; the README still frames registry publication as prepared rather than live, so the clone path is what actually works when Manager comes up empty:
cd ComfyUI/custom_nodes
git clone https://github.com/felipederosilva/ComfyUI-KIE-Nodes-Next
pip install -r ComfyUI-KIE-Nodes-Next/requirements.txt
Restart, then set the key once at Settings → KIE.ai Nodes Next → Connection. It's validated before replacing a working key, and nothing but a masked fingerprint reaches the UI. KIE_API_KEY in the environment overrides the saved key if you're running headless. Dependencies are four small libraries - no torch, no model files, no VRAM cost.
Where people get burned
continue_atoutside the source's length is the most common failure. Check the actual duration first; a value of 60 on a 45-second file can't work.- Instrumental defaults. If you set
promptand got an instrumental back, that's why -instrumentalshippedtrue. - No key throws an explicit error with the settings path in it. Always check that before debugging anything else.
- A timeout isn't a cancellation. The node stops polling at
timeout_seconds; the remote task can still finish. Look atcredits_consumedbefore rerunning. - Mixed installs are refused on startup. If the pack complains that its version and the generated-node build disagree, delete the
ComfyUI-KIE-Nodes-Nextfolder and reinstall. - V5.5 sits in the discontinued tier per KIE's docs. New work should use the V6 sibling; this one earns its keep reproducing existing renders.
Worth saying out loud: extension quality degrades with distance. Adding ten seconds to a track usually sounds seamless; adding two minutes tends to wander. Chain short extensions and re-check the seam each time rather than asking for one long one.
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| upload_url | STRING | https://storage.example.com/upload | The URL of the source audio file to extend. Required. Source audio (`upload_url`) is enough to generate. Ensure the uploaded audio does not exceed 8 minutes in length. |
| prompt | STRING | Extend the music with more relaxing notes | Lyrics for the extended audio. Optional. - Used as lyrics only when `lyrics` is not provided. If `lyrics` is present, `prompt` is not used as lyrics. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters. - Not required. Source audio (`upload_url`) is enough to generate. - Do not pass this parameter when `instrumental` is `true`. |
| instrumentalopt | BOOLEAN | true | Determines whether the audio is instrumental (without lyrics). Optional; defaults to `false`. - If `true`: generate instrumental music (no vocals). Do not pass `lyrics`, `prompt`, or `vocal_gender`. - If `false`: use `lyrics` as lyrics (fall back to `prompt` if `lyrics` is not provided). |
| continue_atopt | FLOAT | 60.00-10000–10000 | The time point (in seconds) from which to start extending the music. - Value range: greater than 0 and less than the total duration of the uploaded audio. - Specifies the position in the original track where the extension should begin. |
| styleopt | STRING | Classical | Music style, e.g., Jazz, Classical, Electronic. Optional. - Not required. Source audio (`upload_url`) is enough to generate. - Character limits by model: - **V6, V6_MINI & V6_WILD**: Maximum 1000 characters - **V5_5 & V5** (Discontinued): Maximum 1000 characters - **V4_5PLUS & V4_5** (Discontinued): Maximum 1000 characters - **V4_5ALL** (Discontinued): Maximum 1000 characters - **V4** (Discontinued): Maximum 200 characters |
| titleopt | STRING | Peaceful Piano Extended | Music title. Optional. - Maximum 100 characters. - Displayed in player interfaces and filenames. |
| negative_tagsopt | STRING | Relaxing Piano | Music styles to exclude from generation |
| vocal_genderopt | COMBO | m | Vocal gender preference for the singing voice. Optional. Use 'm' for male and 'f' for female. Based on practice, this parameter can only increase the probability but cannot guarantee adherence to male/female voice instructions. Do not pass this parameter when `instrumental` is `true`. |
| style_weightopt | FLOAT | 0.650–1 | Strength of adherence to the specified style. Optional. Range 0–1, up to 2 decimal places. |
| weirdness_constraintopt | FLOAT | 0.650–1 | Controls experimental/creative deviation. Optional. Range 0–1, up to 2 decimal places. |
| audio_weightopt | FLOAT | 0.650–1 | Balance weight for audio features vs. other factors. Optional. Range 0–1, up to 2 decimal places. |
| persona_idopt | STRING | persona_123 | Persona ID or Voice ID to apply to the generated music. Optional. Use this to apply a specific persona style to your music generation. To generate a Persona ID, use the [Generate Persona](https://docs.kie.ai/suno-api/generate-persona) endpoint to create a personalized music Persona based on generated music. To generate a Voice ID, use the [Generate Voice](https://docs.kie.ai/suno-api/suno-voice-generate) endpoint. |
| persona_modelopt | COMBO | style_persona | The persona model is only available for models version V5 (Discontinued), V5_5 (Discontinued), V6, V6_MINI, and V6_WILD. |
| lyricsopt | STRING | [Verse] Keep the melody flowing Into a gentle bridge [Chorus] Let the piano rise and fall | Lyrics for the extended audio. Optional. - Takes priority over `prompt` as lyrics. If omitted, `prompt` is used as lyrics when provided. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters. - Not required. Source audio (`upload_url`) is enough to generate. - Do not pass this parameter when `instrumental` is `true`. |
| varietyopt | INT | 10–4 | Controls the diversity and stylistic variation of generated results. Optional. Integer range 0–4, default 1. - **`0`**: off (exact style) — fully off, strictly the same style - **`1`**: normal (balanced variety) — default, balances stability and diversity - **`2`**: high (distinct styles) — produces results with clearly different styles - **`3`**: extra (bold exploration) — higher variation, encourages bold exploration of different styles - **`4`**: max (unreasonably varied) — maximum diversity; results may differ in style very significantly |
| timeout_secondsopt | INT | 120030–7200 | — |
| callback_urlopt | STRING | Optional KIE callback URL. Leave empty for normal ComfyUI use. |
Outputs (7)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |
| url | STRING | — |
| all_urls_json | STRING | — |
| task_id | STRING | — |
| raw_json | STRING | — |
| credits_consumed | FLOAT | — |
| credits_left | FLOAT | — |