GET
/v1/schemas/elevenlabs/audio/v1/text-to-dialogue/stream/with-timestamps
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace2822892612f818acc2e50f317b3f53a619adac6e296acc9cb15ec1fdc1a24061{
"fetchedAt": 1793769627,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
13 properties · 1 required · 4 $defs| property | type | description | constraints |
|---|---|---|---|
| inputs* | DialogueInput[] | A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. The maximum number of unique voice IDs is 10. For reliable generation, keep the total character count across all `inputs[].text` values at or below 2,000 charac… | |
| model_id | string | Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. | default: "eleven_v3" |
| language_code | string | Language code (ISO 639-1) used to enforce a language for the model and text normalization. If the model does not support the provided language code, it will be ignored. This parameter is not supported for multilingual_v2 models. | nullable |
| settings | ToDialogueSettingsResponseModel | Settings controlling the dialogue generation. | nullable |
| pronunciation_dictionary_locators | PronunciationDictionaryVersionLocatorRequestModel[] | A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request | nullable |
| seed | integer | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295. | nullable |
| apply_text_normalization | enum | This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applie… | auto | on | off · default: "auto" |
| use_pvc_as_ivc | boolean | Whether to use the IVC version of a professional voice. This may improve expressiveness and reduce latency. | nullable · deprecated |
| previous_request_ids | string[] | A list of request_ids of dialogue generations that came before this one. Used to condition the model for continuity when splitting a large task into multiple requests. A maximum of 3 request_ids can be sent. The last request_id is the audio which is closest to the current request. Not supported by every model. | nullable |
| next_request_ids | string[] | A list of request_ids of dialogue generations that come after this one. Useful for maintaining continuity when regenerating a clip in the middle of a sequence. A maximum of 3 request_ids can be sent. The first request_id is the audio which is closest to the current request. Not supported by every model. | nullable |
| previous_text | string | The text that comes immediately before this generation, used to condition the model for prosodic continuity. A maximum of 100 characters can be sent. Not supported by every model. | length ≤ 100 · nullable |
| future_text | string | The text that comes immediately after this generation, used to condition the model for prosodic continuity. A maximum of 100 characters can be sent. Not supported by every model. | length ≤ 100 · nullable |
| audio_effects | EffectsSpec-Input | Audio effects applied to generated speech: a filter preset, perceived distance, a reverb environment, a background noise bed, and stereo panning. Leave every field at its default to get unprocessed audio. | nullable |
Types
4 $defsDialogueInputobject
| text* | string | The text to be converted into speech. | |
| voice_id* | string | The ID of the voice to be used for the generation. |
EffectsSpec-Inputobject
Audio effects applied to generated speech: a filter preset, perceived distance, a reverb environment, a background noise bed, and stereo panning. Leave every field at its default to get unprocessed audio.
| filter_preset_id | string | ID of a filter preset that colors the voice, such as `phone` or `old_radio`. List valid IDs with `GET /v1/audio-effects/catalog`. | nullable |
| distance | number | How far the speaker sounds from the microphone, from 0 (close, unchanged) to 1 (far). Higher values roll off low and high frequencies and, when an environment is set, shift the balance from the dry voice toward the reverb. | 0 ≤ n ≤ 1 · default: 0 |
| environment_id | string | ID of a reverb environment that places the voice in a space, such as `small_room` or `hall`. List valid IDs with `GET /v1/audio-effects/catalog`. Reverb is rendered in stereo and adds a tail of up to several seconds after the speech ends. | nullable |
| background_noise_id | string | ID of a background noise bed looped under the voice, such as `cafe` or `keyboard`. List valid IDs with `GET /v1/audio-effects/catalog`. | nullable |
| send_level | number | How much of the voice feeds the reverb, from 0 (none) to 1 (full). Only applies when `environment_id` is set; 0 turns the reverb off. | 0 ≤ n ≤ 1 · default: 1 |
| pan | number | Stereo position of the voice, from -1 (hard left) through 0 (center) to 1 (hard right). Only the voice is panned; reverb and background noise stay centered. | -1 ≤ n ≤ 1 · default: 0 |
PronunciationDictionaryVersionLocatorRequestModelobject
| pronunciation_dictionary_id* | string | The ID of the pronunciation dictionary. | |
| version_id | string | The ID of the version of the pronunciation dictionary. If not provided, the latest version will be used. | nullable |
ToDialogueSettingsResponseModelobject
| stability | number | Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion. | 0 ≤ n ≤ 1 · nullable |
| similarity | number | Determines how strongly the model is guided while generating. Higher values make the model adhere more closely to the voice, at the cost of variation. Not supported by every model. | 0 ≤ n ≤ 1 · nullable |
| clone_strength | number | Controls how closely the output matches your professional voice clone samples (0–1). Lower values sound more versatile, while higher values preserve more of the original voice characteristics. We recommend 0 for most use cases, but if you do run into issues 0.5 could be a good fallback. Applies only to professional voice clones fine-tuned for the selected v4 model. | 0 ≤ n ≤ 1 · nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"elevenlabs","endpointId":"v1/text-to-dialogue/stream/with-timestamps","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}