ENDPOINTSText to Dialogue

Stream dialogue with timestamps

Converts a list of text and voice ID pairs into speech (dialogue) and returns a stream of JSON blobs containing audio as a base64 encoded string and timestamps

Headers

xi-api-keystringRequired

Query Parameters

output_formatenumOptionalDefaults to mp3_44100_128
Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.

Request

This endpoint expects an object.
inputslist of objectsRequired
A list of dialogue inputs, each containing text and a voice ID which will be converted into speech.
model_idstringOptionalDefaults to eleven_v3

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.

language_codestring or nullOptional

Language code (ISO 639-1) used to enforce a language for the model and text normalization. If the model does not support provided language code, an error will be returned.

settingsobject or nullOptional
Settings controlling the dialogue generation.
pronunciation_dictionary_locatorslist of objects or nullOptional

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

seedinteger or nullOptional
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.
apply_text_normalizationenumOptionalDefaults to auto
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 applied, while with 'off', it will be skipped. For 'eleven_turbo_v2_5' and 'eleven_flash_v2_5' models, text normalization can only be enabled with Enterprise plans.
Allowed values:

Response

Stream of transcription chunks
audio_base64string
Base64 encoded audio data
voice_segmentslist of objects
Voice segments for the audio
alignmentobject or null
Timestamp information for each character in the original text
normalized_alignmentobject or null
Timestamp information for each character in the normalized text

Errors