We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Deepgram: Flux TTS
deepgram/flux-ttsTry Deepgram: Flux TTS now
Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
Deepgram: Flux TTS at a glance
- Input price is 181% higher than the median of 34 Speech models.
About Deepgram: Flux TTS
Deepgram: Flux TTS is a text-to-speech model from Deepgram, a provider known for speech and audio infrastructure. It sits in the speech category and is built specifically for turning written English text into spoken audio. If you already route other Deepgram models through api14, this one comes from the same vendor and follows the same general pattern of use.
The model takes text as its only input and produces speech as its only output, so it is a single-purpose synthesis model rather than a general chat or reasoning model. It is designed for natural, expressive English speech. The Flux voice catalog is large: 36 voices are available, including flux-alexis-en, flux-bree-en, flux-brittany-en, flux-brooke-en, flux-bruce-en, flux-cliff-en, flux-cole-en, flux-colin-en, flux-conor-en, flux-donovan-en, flux-drew-en, flux-elise-en, flux-gemma-en, flux-haley-en, flux-hannah-en, flux-heather-en, flux-jack-en, flux-kai-en, flux-kelsey-en, flux-kit-en, flux-maeve-en, flux-marcelo-en, flux-marcus-en, flux-meena-en, flux-meghan-en, flux-miles-en, flux-naveen-en, flux-paige-en, flux-priya-en, flux-rufus-en, flux-sean-en, flux-sharon-en, flux-sienna-en, flux-tanner-en, flux-wade-en and flux-wes-en. No context length is published for this model, and the details list maxOutput as 0, so treat it purely as a synthesis endpoint rather than something you send long conversations to.
The practical uses follow directly from text in, speech out. You can generate voiceovers for videos or narrated walkthroughs, produce audio versions of articles or documentation, build spoken prompts and notifications for apps and phone systems, or add narration to accessibility features. Because many distinct voices ship with the model, you can cast different speakers for different parts of a product, such as a calm voice for instructions and a warmer one for conversational replies, without leaving the same model.
Calling it through api14 works like any other OpenAI-compatible request: send your text to the speech endpoint and set the model id to "deepgram/flux-tts". Choose a voice from the Flux list to control the speaker. Note that the supported parameters list is empty, so you should not assume extra tuning options such as speed, pitch or style controls are exposed here. Stick to the documented fields and the voice selection.
Because no context length is published and maxOutput is 0, this model is not the right fit for tasks that need long text understanding, reasoning, translation or any output other than audio. If you need those, use a text or multimodal chat model instead. Flux TTS is best treated as a focused component in a pipeline: text comes in, English speech comes out.
How to call the Deepgram: Flux TTS API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "deepgram/flux-tts".
import { writeFile } from "node:fs/promises";
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const audio = await client.audio.speech.create({
"model": "deepgram/flux-tts",
"input": "Hello from api14! One API for every model.",
"voice": "alloy",
"response_format": "mp3"
});
await writeFile("speech.mp3", Buffer.from(await audio.arrayBuffer()));
Specifications
- Input
- text
- Output
- speech
- Voices
- 36
Requests on api14 · last 7 days
Deepgram: Flux TTS: frequently asked questions
- How much does the Deepgram: Flux TTS API cost?
- Deepgram: Flux TTS costs Characters $157.50 / 1M characters. It is charged from your USD balance only for successful requests; failed requests are free.
- What can Deepgram: Flux TTS do?
- Deepgram: Flux TTS accepts text and returns speech.
- How do I call Deepgram: Flux TTS from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "deepgram/flux-tts". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Deepgram: Flux TTS?
- Comparable Speech models at a similar price: ElevenLabs: Eleven v4 Turbo, ElevenLabs: Eleven v3 Conversational, ElevenLabs: Eleven Flash v2.5. Each runs through the same API key, so switching is one string.
Deepgram: Flux TTS community
New topicThis community has no topics yet. Open the first one about Deepgram: Flux TTS.