scenario-elevenlabs

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Scenario ElevenLabs Audio

Scenario ElevenLabs 音频

Overview

概述

ElevenLabs covers five audio lanes on Scenario: speech, music, sound effects, dubbing, and voice transforms. Eleven members ship side by side at authoring time, one job each: the deciding move is picking the right member, not coaxing one model into a mode. Discover them with

search

and treat

model_schema_get

as the contract: the members agree on almost nothing.

Connection and the core loop: see the

scenario

skill in this repo; model-agnostic audio work: the

scenario-audio

skill. If a sibling skill named here is missing from your available skills, ask the user to install it (

npx skills add scenario-labs/skills --skill <name>

); unattended, proceed from tool schemas and flag the gap.

ElevenLabs在Scenario上涵盖五大音频赛道：语音、音乐、音效、配音和声音转换。创作阶段，多个Eleven模型成员并行提供，每个负责一项任务：核心是选择合适的模型，而非强行让单个模型适配某种模式。可通过

search

发现这些模型，并将

model_schema_get

视为约定：各模型之间的参数几乎没有共通性。

连接方式与核心流程：参见本仓库中的

scenario

技能；与模型无关的音频处理：使用

scenario-audio

技能。如果你的可用技能中缺少此处提到的同类技能，请让用户安装（命令：

npx skills add scenario-labs/skills --skill <name>

）；若处于无人值守模式，可从工具模式入手并标注缺失项。

Quick reference

快速参考

Job	Member	Deciding inputs
Expressive speech, dialog	Eleven v3	`text` with inline tags
Narration, pinned language	Multilingual 2	`languageCode`
Fast or bulk speech	Turbo 2.5	same shape, lower cost
Music from one prompt	Music v2	`prompt` , `durationSeconds` , `forceInstrumental`
Structured song	Music Advanced v2	required `sections` array
SFX and loops	Sound Effects 2	`text` , `promptInfluence` , `loop`
Localize, protect names	Dubbing v2	`file` , `targetLang` , `keyterms`
Localize, speaker control	Dubbing	`numSpeakers` , `dropBackgroundAudio`
Re-voice a recording	Speech to Speech, Voice Changer	`audio` (up to 5 min) plus a voice
Clean a noisy voice	Voice Isolator	`audio`

The speaking members share one voice contract:

voiceId

takes a cloned ElevenLabs voice and always wins;

publicVoice

picks a preset (21 at authoring time) and is ignored beside it; neither set means the Adam preset. Voice Changer is Speech to Speech plus delivery dials (

stability

similarityBoost

styleExaggeration

useSpeakerBoost

). WAV output exists on the TTS members alone;

outputFormat

elsewhere is MP3 or Opus, absent on Dubbing and Voice Isolator.

seed

gives repeatability, except on Sound Effects 2, both Dubbing members, and Voice Isolator. Cost rides the content:

text

on TTS (40,000 characters at authoring time),

durationSeconds

on Music v2,

sections

on Advanced,

file

audio

on the dubbing and voice members, so

dry_run

long jobs and member comparisons.

任务	模型成员	核心输入参数
富有表现力的语音、对话	Eleven v3	带内联标签的 `text`
旁白、固定语言	Multilingual 2	`languageCode`
快速或批量语音生成	Turbo 2.5	参数结构相同，成本更低
单提示生成音乐	Music v2	`prompt` 、 `durationSeconds` 、 `forceInstrumental`
结构化歌曲	Music Advanced v2	必填的 `sections` 数组
音效与循环音	Sound Effects 2	`text` 、 `promptInfluence` 、 `loop`
本地化、专有名称保护	Dubbing v2	`file` 、 `targetLang` 、 `keyterms`
本地化、说话人控制	Dubbing	`numSpeakers` 、 `dropBackgroundAudio`
录音重新配音	Speech to Speech、Voice Changer	`audio` （最长5分钟）+ 声音设置
噪音语音降噪	Voice Isolator	`audio`

语音类模型共享一套声音约定：

voiceId

用于指定克隆的ElevenLabs声音，且优先级始终最高；

publicVoice

用于选择预设声音（创作阶段共有21种），若同时设置了

voiceId

则会被忽略；两者都未设置时，默认使用Adam预设。Voice Changer是在Speech to Speech基础上增加了表达风格调节参数（

stability

、

similarityBoost

、

styleExaggeration

、

useSpeakerBoost

）。仅TTS类模型支持WAV输出；其他模型的

outputFormat

为MP3或Opus，Dubbing和Voice Isolator不支持该参数。

seed

参数可保证结果可复现，但Sound Effects 2、两个Dubbing模型以及Voice Isolator不支持。成本由内容决定：TTS按

text

字符数计费（创作阶段上限为40,000字符），Music v2按

durationSeconds

计费，Advanced版按

sections

计费，配音和声音类模型按

file

或

audio

计费，因此长任务和模型对比请先使用

dry_run

。

Speech: tags on v3, dials elsewhere

语音：v3支持标签，其他模型用调节参数

Eleven v3 reads inline audio tags in the text, [whispers], [excited], [sighs], to steer delivery moment to moment across 70+ languages, and carries multi-speaker dialogue. Multilingual 2 and Turbo 2.5 do not read tags: direction there lives in

stability

styleExaggeration

, and

speed

(0.7 to 1.2), and

languageCode

(ISO 639-1) pins the language, a field v3 lacks. Turbo trades expressiveness for cost, roughly half the other two per run at authoring time.

Eleven v3可识别文本中的内联音频标签（如[whispers]、[excited]、[sighs]），能够在70多种语言中逐时刻调整表达风格，还支持多说话人对话。Multilingual 2和Turbo 2.5不识别标签：这类模型的风格控制通过

stability

、

styleExaggeration

和

speed

（范围0.7到1.2）实现，且通过

languageCode

（ISO 639-1标准）固定语言——这是v3没有的字段。Turbo以牺牲表现力换取更低成本，创作阶段单次运行成本约为另外两个模型的一半。

Music: one prompt or thirty sections

音乐：单提示生成或三十段分段创作

Music v2 takes one

prompt

(mood, genre, instruments, tempo),

durationSeconds

(3 to 600 at authoring time, cost impact), and

forceInstrumental

to suppress vocals: asking in prose is unreliable. Music Advanced v2 requires

sections

, up to 30 ordered segments at authoring time, each with

text

, its own

durationSeconds

(3 to 120),

positiveStyles

and

negativeStyles

(up to 10 each), and

contextAdherence

(high binds a segment to its neighbors, low frees it). Section grammar: square brackets label ([Verse], [Chorus]), curly braces direct ({soft piano intro}), and plain text is sung as lyrics. Advanced has no instrumental flag, so any plain text will be sung. Neither music member takes

numOutputs

: one run is one composition, and sung lyrics land differently on every draw, so a batch of takes is several parallel runs with distinct

seed

values, each priced alone on its duration, which costs what a batch field would have and returns separate files with real boundaries. Two

[Verse]

blocks in one run to get two takes returns one file with no split point.

Music v2接收单个

prompt

（可包含情绪、流派、乐器、节奏）、

durationSeconds

（创作阶段范围为3到600秒，影响成本），以及用于抑制人声的

forceInstrumental

参数：用自然语言描述要求纯音乐是不可靠的。Music Advanced v2要求传入

sections

参数，创作阶段最多支持30个有序分段，每个分段包含

text

、独立的

durationSeconds

（3到120秒）、

positiveStyles

和

negativeStyles

（各最多10个），以及

contextAdherence

（值高表示分段与相邻分段关联性强，值低则更自由）。分段语法：方括号用于标注段落（如[Verse]、[Chorus]），花括号用于指示风格（如{soft piano intro}），纯文本则作为歌词演唱。Advanced版没有纯音乐开关，因此任何纯文本都会被演唱。两个音乐模型都不支持

numOutputs

参数：一次运行生成一首作品，且每次生成的歌词演唱效果都不同，因此批量生成多个版本需要使用不同的

seed

值并行运行多次，每次按时长单独计费，总成本与批量参数的方式相当，且返回的是带有明确边界的独立文件。如果在一次运行中写两个

[Verse]

块来获取两个版本，最终只会得到一个没有分割点的文件。

Dubbing replaces the track, not the lips

配音：替换音轨而非口型

Both Dubbing members take an audio or video

file

with a required

targetLang

, and the output follows the input kind: video in, dubbed video out. Neither re-animates lips. Source auto-detection is spelled differently:

sourceLang: "auto"

on v2, an empty string on the older member. Pick v2 for

keyterms

(names, brands, and jargon preserved verbatim through translation); pick the older Dubbing for

numSpeakers

(0 auto-detects, up to 10),

dropBackgroundAudio

disableVoiceCloning

, and

highestResolution

video. Their prices differ several-fold, so

dry_run

both when either fits. Speech to Speech, Voice Changer and Voice Isolator, by contrast, take

audio

only, whatever the catalog blurb says: for a clip, pull the track with

model_scenario-audio-extract

, run the member, then lay the result over the clip in

model_scenario-compose-video

, the clip as a video layer with

mute: true

(fixed ids: each is Scenario's single deterministic tool for its operation, so discovery would only re-derive it). The same compositor lays a Music v2 bed under a video; layer contract in

scenario-video-assembly

两个Dubbing模型都接收音频或视频

file

，且必填

targetLang

参数，输出类型与输入一致：输入视频则输出配音后的视频。两者都不支持口型重绘。源语言自动检测的参数写法不同：v2版用

sourceLang: "auto"

，旧版则用空字符串。选择v2版可使用

keyterms

功能（人名、品牌名和专业术语在翻译中会原样保留）；选择旧版Dubbing可使用

numSpeakers

（0表示自动检测，最多10人）、

dropBackgroundAudio

、

disableVoiceCloning

以及

highestResolution

视频参数。两者的价格相差数倍，因此如果都适用的话，都先跑

dry_run

对比。相比之下，Speech to Speech、Voice Changer和Voice Isolator仅接收

audio

输入，不管产品介绍怎么说：如果要处理视频片段，先用

model_scenario-audio-extract

提取音轨，运行模型后，再通过

model_scenario-compose-video

将结果叠加到片段上，将原片段设为

mute: true

的视频层（这些是固定ID：每个都是Scenario对应操作的唯一确定性工具，因此无需再搜索发现）。同一个合成器也可以将Music v2生成的背景音乐铺在视频下方；层的约定详见

scenario-video-assembly

。

Worked example: dub a trailer into Spanish

实操示例：将预告片配音为西班牙语

```
search
```
with
```
target="models"
```
,
```
query="elevenlabs dubbing"
```
,
```
public=true
```
. Prefer the newest non-deprecated hit, e.g.
```
model_elevenlabs-dubbing-v2
```
(a live hit at authoring time: re-discover each session).
```
model_schema_get
```
with that id: fields and defaults before anything else.
```
upload_asset
```
the trailer video (see the
```
scenario
```
skill) to get an asset id.

model_run

with that

model_id

dry_run=true

, and the exact

parameters={"file": "asset_x", "targetLang": "es", "keyterms": ["Aetherfall", "Kestrel Squad"]}

. The file drives the price: re-estimate per input.

Repeat
```
model_run
```
with
```
wait=false
```
, then
```
jobs_wait
```
with the returned job id, re-called with
```
pending_job_ids
```
on timeout, never a second
```
model_run
```
.
```
asset_display
```
the result (a video, because the input was) and confirm the keyterms survived;
```
asset_download
```
with no
```
format
```
to save it.

使用
```
search
```
，设置
```
target="models"
```
、
```
query="elevenlabs dubbing"
```
、
```
public=true
```
。优先选择最新的未弃用结果，例如
```
model_elevenlabs-dubbing-v2
```
（创作阶段的有效结果：每次会话都需重新搜索确认）。
用该ID调用
```
model_schema_get
```
：先确认所有字段和默认值再进行后续操作。
上传预告片视频（参见
```
scenario
```
技能），获取资源ID。

调用

model_run

，传入

model_id

、

dry_run=true

，以及准确的参数

parameters={"file": "asset_x", "targetLang": "es", "keyterms": ["Aetherfall", "Kestrel Squad"]}

。价格由文件决定：每次输入都要重新估算。

再次调用
```
model_run
```
，设置
```
wait=false
```
，然后用返回的任务ID调用
```
jobs_wait
```
，超时则用
```
pending_job_ids
```
重新调用，切勿重复调用
```
model_run
```
。
用
```
asset_display
```
查看结果（因为输入是视频，所以输出也是视频），确认关键词保留正确；不带
```
format
```
参数调用
```
asset_download
```
保存文件。

Common mistakes

常见错误

Setting
```
publicVoice
```
next to
```
voiceId
```
and expecting it to apply: a set
```
voiceId
```
always wins.
Inline tags on Multilingual 2 or Turbo 2.5: that grammar is Eleven v3's; elsewhere a tag can be read aloud.
Writing "instrumental" in a Music v2 prompt instead of setting
```
forceInstrumental
```
; on Music Advanced there is no flag and plain section text is always sung.
Expecting lip-sync from Dubbing: the track changes, the picture does not.
Reaching for
```
numOutputs
```
on the music members, or repeating one long run hoping for a different take without changing
```
seed
```
: same seed and settings reproduce the same music.
Carrying one member's caps to another: 40,000 characters, 600 seconds, 30 sections, and 5 minutes of input audio are each true of one lane and false of the next.

同时设置
```
publicVoice
```
和
```
voiceId
```
并期望前者生效：只要设置了
```
voiceId
```
，它的优先级始终最高。
在Multilingual 2或Turbo 2.5中使用内联标签：该语法是Eleven v3专属的；在其他模型中，标签会被直接朗读出来。
在Music v2的提示词中写“instrumental”而不是设置
```
forceInstrumental
```
参数；Music Advanced版没有该开关，分段中的纯文本总会被演唱。
期望Dubbing支持口型同步：配音只会替换音轨，画面不会变化。
在音乐模型中使用
```
numOutputs
```
参数，或者不改变
```
seed
```
就重复运行长任务期望得到不同版本：相同的种子和设置只会生成相同的音乐。
将一个模型的限制套用到另一个模型上：40,000字符、600秒、30个分段、5分钟输入音频上限分别对应不同赛道，不能通用。