Text To Dialogue Streaming 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

output_format'mp3_22050_32' | 'mp3_24000_48' | 'mp3_44100_32' | 'mp3_44100_64' | 'mp3_44100_96' | 'mp3_44100_128' | 'mp3_44100_192' | 'pcm_8000' | 'pcm_16000' | 'pcm_22050' | 'pcm_24000' | 'pcm_32000' | 'pcm_44100' | 'pcm_48000' | 'ulaw_8000' | 'alaw_8000' | 'opus_48000_32' | 'opus_48000_64' | 'opus_48000_96' | 'opus_48000_128' | 'opus_48000_192'

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.

enable_loggingboolean

When enable_logging is set to false zero retention mode will be used for the request. This will mean history features are unavailable for this request, including request stitching. Zero retention mode may only be used by enterprise customers.

xi-api-keystring nullable

Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.

Request body

model_idstring

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 nullable

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.

seedinteger nullable

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_normalization'auto' | 'on' | 'off'

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.

Example request

{
  "inputs": [
    {
      "text": "Hello, how are you?",
      "voice_id": "bYTqZQo3Jz7LQtmGTgwi"
    },
    {
      "text": "I'm doing well, thank you!",
      "voice_id": "6lCwbsX1yVjD49QmpkTR"
    }
  ],
  "settings": {
    "stability": 0.5
  },
  "pronunciation_dictionary_locators": [
    {
      "pronunciation_dictionary_id": "test",
      "version_id": "id2"
    }
  ],
  "seed": 12345
}

Response

Stream of transcription chunks

audio_base64string required

Base64 encoded audio data

Example response

{
  "alignment": {
    "character_end_times_seconds": [
      0.1,
      0.2
    ],
    "character_start_times_seconds": [
      0,
      0.1
    ],
    "characters": [
      "H",
      "e"
    ]
  },
  "audio_base64": "base64_encoded_audio_chunk",
  "normalized_alignment": {
    "character_end_times_seconds": [
      0.1,
      0.2
    ],
    "character_start_times_seconds": [
      0,
      0.1
    ],
    "characters": [
      "H",
      "e"
    ]
  },
  "voice_segments": [
    {
      "character_end_index": 2,
      "character_start_index": 0,
      "dialogue_input_index": 0,
      "end_time_seconds": 0.2,
      "start_time_seconds": 0,
      "voice_id": "VEDscrYI8uIMttlO2Ztu"
    }
  ]
}

v4

Text To Dialogue Streaming With Timestamps

Query parameters

Headers

Request body

Example request

Response

Example response