DEdeepgram
audio

Flux Text to Speech (batch)

Changed on

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.

post/v2/speak

Request

  • Base URL
    https://api.deepgram.com
  • Auth
    API key in header Authorization

Query parameters

callbackstring

URL to which we'll make the callback request

callback_method'POST' | 'PUT'

HTTP method by which the callback request will be made

mip_opt_outboolean

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

string
OR
string[]

Label your requests for the purpose of identification during usage reporting

'8000' | '16000' | '24000' | '32000' | '40000' | '48000'

Encoding - mp3(default). Supported bitrates - 8000, 16000, 24000, 32000, 40000, 48000(default) bps.

OR
integer
OR
integer

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

'none'

No container.

OR
'wav'

Encoding - linear16. Supported container - wav (default), or no container.

OR
'wav'

Encoding - mulaw. Supported container - wav (default), or no container.

OR
'wav'

Encoding - alaw. Supported container - wav (default), or no container.

OR
'ogg'

Encoding - opus. Supported container - ogg (default).

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

'linear16'

Encoding - linear16. Uncompressed, high-quality audio format often used for telephony or audio processing.

OR
'flac'

Encoding - flac. Lossless audio format for high-quality compression.

OR
'mulaw'

Encoding - mulaw. Compressed audio format commonly used in telephony.

OR
'alaw'

Encoding - alaw. Similar to mulaw but used in international telephony.

OR
'mp3'

Encoding - mp3. Popular compressed audio format for music and streaming.

OR
'opus'

Encoding - opus. High-compression audio format optimized for real-time communications.

OR
'aac'

Encoding - aac. Advanced audio format offering better quality at smaller file sizes than mp3.

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

expressivity'-2' | '-1' | '0' | '1' | '2'

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.

modelstring required

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.

'8000' | '16000' | '24000' | '32000' | '44100' | '48000'

Encoding - linear16. Supported sample rates - 8000, 16000, 24000, 32000, 44100, 48000 Hz.

OR
'8000' | '16000'

Encoding - mulaw. Supported sample rates - 8000, 16000 Hz.

OR
'8000' | '16000'

Encoding - alaw. Supported sample rates - 8000, 16000 Hz.

OR
'8000' | '16000' | '22050' | '32000' | '48000'

Encoding - flac. Supported sample rates - 8000, 16000, 22050, 32000, 48000 Hz.

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

speednumber double

Speaking rate multiplier that adjusts the pace of generated speech while preserving natural prosody and voice quality. Accepted values run 0.5 to 1.5 in 0.05 increments. Not yet supported in all languages. When the text contains an inline pause marker, speed is capped at 1.15 (PAUSE_SPEED_CAP_EXCEEDED above that). A value other than 1.0 cannot be combined with inline pronunciation controls (CONTROL_COMBINATION_INVALID).

priority'low'

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

Request body

textstring required

The text content to be converted to speech. For English, German, Dutch, French, Hindi, Italian, Japanese, Portuguese, Russian and Spanish, the server normalizes the text (numbers, dates, abbreviations) before synthesis; the other languages are in Early Access without text normalization, so write numbers and dates out in words. May contain inline pause controls (\{pause:500ms\}, 500-3000 ms in 100 ms steps, at most 8 per request) and inline pronunciation controls (\{"word": "...", "pronounce": "<IPA>"\}, Early Access). Pronunciation cannot be combined with pause or with a speed other than 1.0, and speed is capped at 1.15 when a pause is present. See Speed, Pause, Pronunciation.

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.

request_idstring uuid required

Unique identifier for tracking the asynchronous request

Changes