Use this page as the source of truth for publicly documented TTS model IDs.
Model overview
Public model ID list
V3 language scope
- Supported language count:
98 - Excluded from support:
Kirghiz,Lingala
Open V3 language code list
View the complete supported language and code table.
Accent model (myvocal_v3_accent_enhance)
The Accent model has its own language contract. It is not the same set as myvocal_v3.
- Supported language count:
40language codes, plusauto. - Omitting
languageis equivalent toauto. - A code outside this list is rejected with
code = 10004. This includes plain V3 codes the Accent model does not support, such ashmn. - Legacy mapped enum values (for example
US_ENGLISH) are not Accent codes. Useen.
- Voices: use the compatible voices returned by
GET /sound_clone/api/v1/voices?modelId=myvocal_v3_accent_enhance. That list includes your own compatible voices and the prebuilt voices available to your API key. A voice listed there is a selection aid, not a guarantee that a later generation will succeed. voiceSettings.stability: a value inside the legal range (0.1to1) is accepted for compatibility but has no effect on this model. Out-of-range values are still rejected withcode = 10006.- Prompt tags: inline
[tag]prompt control is documented formyvocal_v3. It is not documented as equivalent for the Accent model; send plain text. - Character metering, plan limits and rates stay the same as the other TTS models.
Default path vs explicit modelId
- Default path: omit
modelIdand follow current V2/default mapping rules. - Explicit V3 path: set
modelIdtomyvocal_v3. - Explicit Accent path: set
modelIdtomyvocal_v3_accent_enhance.
V2 to V3 migration guidance
- Keep your V2 flow as fallback.
- Add a feature flag for
modelId: "myvocal_v3". - Use explicit
languageif you want deterministic target language output. - Omit
languagefor auto-detect behavior on V3. - Roll out with traffic slices and monitor output quality.
Migration to the Accent model
The table describes what changes when you move from the default/V2 path or frommyvocal_v3 to
myvocal_v3_accent_enhance.
