Flux Text to Speech (batch)

Synthesize a complete block of text into a single audio response using Deepgram’s Flux TTS batch (REST) API. Use this for pre-rendering fixed audio (IVR prompts, notifications, narration) where the whole text is known up front and you don’t need incremental playback or interruption.

Authentication

AuthorizationToken

Use Authorization: Token <API_KEY> Example: Authorization: Token 12345abcdef

AuthorizationBearer

Use Authorization: Bearer <JWT> Example: Authorization: Bearer eyJhbGciOiJ...

Query parameters

callbackstringOptional

URL to which we'll make the callback request

callback_methodenumOptionalDefaults to POST

HTTP method by which the callback request will be made

Allowed values:

mip_opt_outbooleanOptionalDefaults to false

Opts out requests from the Deepgram Model Improvement Program. Refer to our Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip

tagstring or list of stringsOptional

Label your requests for the purpose of identification during usage reporting

bit_rateenum or integerOptionalDefaults to 48000

The bitrate of the audio in bits per second. Choose from predefined ranges or specific values based on the encoding type.

containerenumOptionalDefaults to wav

Container specifies the file format wrapper for the output audio. The available options depend on the encoding type.

encodingenumOptionalDefaults to mp3

Encoding allows you to specify the expected encoding of your audio output

expressivityenumOptionalDefaults to 0

Expressive range of the generated speech, on a calm-to-animated axis. Accepted values: -2, -1, 0, 1, 2. 0 (the default) is the voice’s tuned delivery and the production-validated setting, with -2 the calm end of the range and 2 the animated end. Supported on all Flux voices; applies to the whole request. Beta: behavior may change in future model versions, and non-default values increase the risk of hallucinations and pronunciation errors; audition before shipping. An invalid value is rejected with a 400 — EXPRESSIVITY_OUT_OF_RANGE for a value outside the range, EXPRESSIVITY_INCREMENT_INVALID for a fractional value. See Expressivity.

Expressive range of the generated speech, on a calm-to-animated axis. Accepted values: `-2`, `-1`, `0`, `1`, `2`. `0` (the default) is the voice's tuned delivery and the production-validated setting, with `-2` the calm end of the range and `2` the animated end. Supported on all Flux voices; applies to the whole request. Beta: behavior may change in future model versions, and non-default values increase the risk of hallucinations and pronunciation errors; audition before shipping. An invalid value is rejected with a `400` — `EXPRESSIVITY_OUT_OF_RANGE` for a value outside the range, `EXPRESSIVITY_INCREMENT_INVALID` for a fractional value. See [Expressivity](/docs/tts-expressivity).

Allowed values:

modelstringRequired

Flux TTS model used to synthesize the submitted text, in the form flux-{voice}-{language} (for example, flux-alexis-en). Required; unlike the v1 (Aura) endpoint there is no default and only flux models are accepted. English-only at launch.

sample_rateenumOptionalDefaults to 24000

Sample Rate specifies the sample rate for the output audio. Based on the encoding, different sample rates are supported. For some encodings, the sample rate is not configurable

speedenumOptionalDefaults to 1

Speaking rate multiplier that adjusts the pace of generated speech while preserving natural prosody and voice quality. Accepted values run 0.85 to 1.15 in 0.05 increments. Not yet supported in all languages.

priorityenumOptional

Processing priority for asynchronous (callback) requests. The only supported value is low.

Allowed values:

Request

Transform text to speech

textstringRequired

The text content to be converted to speech. The server normalizes and preprocesses the text before synthesis. Inline pause and pronunciation controls are not yet applied; they are stripped from the text before synthesis.

Response

Returns the synthesized audio in the requested encoding as a binary stream. When a callback URL is supplied, the request is processed asynchronously and the response body is instead a JSON acknowledgement (Content-Type application/json) of the form {“request_id”: ”…”}, with the audio delivered to the callback URL. Because this endpoint is typed as a binary audio stream, SDK callers that set callback receive this JSON acknowledgement through the audio byte iterator as raw bytes and must join the chunks and parse request_id themselves.

Returns the synthesized audio in the requested encoding as a binary stream. When a `callback` URL is supplied, the request is processed asynchronously and the response body is instead a JSON acknowledgement (Content-Type `application/json`) of the form {"request_id": "..."}, with the audio delivered to the callback URL. Because this endpoint is typed as a binary audio stream, SDK callers that set `callback` receive this JSON acknowledgement through the audio byte iterator as raw bytes and must join the chunks and parse `request_id` themselves.

request_idstringformat: "uuid"

Unique identifier for tracking the asynchronous request

Errors

400

Bad Request Error

1	import requests
2
3	url = "https://api.deepgram.com/v2/speak"
4
5	querystring = {"expressivity":"1","model":"flux-alexis-en","speed":"1.05"}
6
7	payload = { "text": "Your appointment is confirmed for 3pm tomorrow." }
8	headers = {
9	"Authorization": "Token <apiKey>",
10	"Content-Type": "application/json"
11	}
12
13	response = requests.post(url, json=payload, headers=headers, params=querystring)
14
15	print(response.json())

1	{
2	"request_id": "a1b2c3d4-e5f6-7890-ab12-cd34ef567890"
3	}