EL โ
Endpoint: POST https://vod.intl.tencentcloudapi.comAction: CreateAigcAudioTask
EL (ElevenLabs) is an audio generation model. The compose_* versions generate music from a prompt, and the sound_t2s_* versions generate sound effects from text. Music versions compose_v2, compose_v2.5, and compose_detailed_v2.5, and sound effect versions sound_t2s_v2 and sound_t2s_v3 are available; compose_v2.5, compose_detailed_v2.5, and sound_t2s_v3 were launched on 2026-11-16.
See Version differences to pick a version and Calling by version for request examples.
Basic Information โ
| Item | Value |
|---|---|
| ModelName | EL |
| ModelVersion | Music: compose_v2 / compose_v2.5 / compose_detailed_v2.5; sound effects: sound_t2s_v2 / sound_t2s_v3 |
| SceneType | Not required โ leave it empty |
| Use | compose_* music, sound_t2s_* sound effects |
Version differences โ
| ModelVersion | Type | Upstream ElevenLabs API | Upstream model |
|---|---|---|---|
compose_v2 | Music | Compose music | music_v2 |
compose_v2.5 | Music | Compose music | music_v2_5 |
compose_detailed_v2.5 | Music (detailed) | Compose music with details | music_v2_5 |
sound_t2s_v2 | Sound effects | Sound effects | โ |
sound_t2s_v3 | Sound effects | Sound effects | โ |
How to choose:
- General music from a prompt โ
compose_v2.5(the latest);compose_v2remains available. - Music via the "compose with details" endpoint โ
compose_detailed_v2.5. - Short sound effects โ
sound_t2s_v3(the latest);sound_t2s_v2remains available.
The "Upstream model" column is inferred from the version names and the upstream
model_idvalues (music_v2/music_v2_5); the integration guide does not state the mapping. The upstream models of the two sound effect versions are not stated, so they are left empty;sound_t2s_v3shares the same parameter table asv2(Duration[1, 30]), and the guide does not describe the difference in output.โ ๏ธ Upstream, "compose with details" additionally accepts a section-level
composition_planand returns metadata alongside the audio. The integration guide only documentsPrompt+OutputConfigforcompose_detailed_v2.5, and does not say whethercomposition_plancan be passed throughAdditionalParameters, or whether the extra metadata is returned. Treat these as unconfirmed and verify with a test call before relying on them.
Request Parameters โ
| Parameter | Required | Type | Description |
|---|---|---|---|
SubAppId | Optional | Integer | VOD application ID |
ModelName | Optional | String | EL |
ModelVersion | Optional | String | compose_v2 / compose_v2.5 / compose_detailed_v2.5 / sound_t2s_v2 / sound_t2s_v3 |
SceneType | Optional | String | Not required |
Prompt | Optional | String | Style / instrument / scene description (sound effects: describe the sound) |
OutputConfig | Optional | Object | Output settings, see below |
OutputConfig โ
| Field | Applies to | Description |
|---|---|---|
StorageMode | All versions | Temporary: not stored in VOD; a temporary URL valid for 7 days is returned in the event notification. Permanent: stored in VOD; a FileId is returned |
Duration | sound_t2s_* only | Sound effect length in seconds, [1, 30] |
Calling by version โ
Music (compose_v2.5) โ
Same call for compose_v2 โ just change ModelVersion.
{
"ModelName": "EL",
"ModelVersion": "compose_v2.5",
"Prompt": "A quiet electronic instrumental for a night drive",
"SubAppId": 123456789,
"OutputConfig": {
"StorageMode": "Temporary"
}
}Detailed music (compose_detailed_v2.5) โ
{
"ModelName": "EL",
"ModelVersion": "compose_detailed_v2.5",
"Prompt": "Cinematic orchestral trailer music, slow build to an epic climax",
"SubAppId": 123456789,
"OutputConfig": {
"StorageMode": "Permanent"
}
}Sound Effects (sound_t2s_v3) โ
Same call for sound_t2s_v2 โ just change ModelVersion.
{
"ModelName": "EL",
"ModelVersion": "sound_t2s_v3",
"Prompt": "Rain on a metal roof",
"SubAppId": 123456789,
"OutputConfig": {
"StorageMode": "Temporary",
"Duration": 6
}
}Response Example โ
{
"Response": {
"TaskId": "<task-id>",
"RequestId": "<request-id>"
}
}Query the completion result with DescribeTaskDetail. See Audio Result Structure.
Special Settings โ
OutputConfig.Durationonly applies to the sound effect versionssound_t2s_v2/sound_t2s_v3(1โ30 seconds). It is not applied to thecompose_*music versions.- No version specifies
SceneType. - Upstream, a plain prompt is limited to
4100characters (reference value from the ElevenLabs API, not stated in the VOD guide).