Using Deepgram Text-to-Speech (Rust SDK)

Use this skill when generating audio from text with the Rust SDK's Speak surface.

When to use this product

• Converting text into audio files with speaktofile(...).
• Streaming TTS bytes with speaktostream(...).
• Selecting Aura voices and output encodings with speak::options::Options.

Authentication

For a TTS-only install:

[dependencies]
deepgram = { version = "0.10.0", default-features = false, features = ["speak"] }
tokio = { version = "1", features = ["full"] }
futures = "0.3"
# Only add `bytes = "1"` if you need to name `bytes::Bytes` in your own signatures.
# The code below relies on type inference and does not import bytes directly.

let dg = deepgram::Deepgram::new(std::env::var("DEEPGRAM_API_KEY")?)?;

• API keys use Authorization: Token <api_key>.
• The crate does not expose a TTS WebSocket client today; the supported Rust surface is REST returning a saved file or a stream of bytes.

Quick start

Quick start: save audio to a file

use std::{path::Path, time::Instant};

use deepgram::{
    speak::options::{Container, Encoding, Model, Options},
    Deepgram,
};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let api_key = std::env::var("DEEPGRAM_API_KEY")?;
    let dg = Deepgram::new(&api_key)?;

    let options = Options::builder()
        .model(Model::AuraAsteriaEn)
        .encoding(Encoding::Linear16)
        .sample_rate(16000)
        .container(Container::Wav)
        .build();

    let start = Instant::now();
    dg.text_to_speech()
        .speak_to_file("Hello from Rust.", &options, Path::new("output.wav"))
        .await?;

    println!("Time to download audio: {:.2?}", start.elapsed());
    Ok(())
}

Quick start: stream response bytes

use deepgram::{
    speak::options::{Container, Encoding, Model, Options},
    Deepgram,
};
use futures::stream::StreamExt;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let api_key = std::env::var("DEEPGRAM_API_KEY")?;
    let dg = Deepgram::new(&api_key)?;

    let options = Options::builder()
        .model(Model::AuraAsteriaEn)
        .encoding(Encoding::Linear16)
        .sample_rate(16000)
        .container(Container::Wav)
        .build();

    let mut stream = dg
        .text_to_speech()
        .speak_to_stream("Hello from Rust.", &options)
        .await?;

    while let Some(chunk) = stream.next().await {
        println!("received {} bytes", chunk.len());
    }

    Ok(())
}

Key parameters

• Entrypoints: Deepgram::texttospeech(), Speak::speaktofile(...), Speak::speaktostream(...).
• TTS Options builder fields: model, encoding, samplerate, container, bitrate.
• Model enum lives in deepgram::speak::options::Model and includes voices such as AuraAsteriaEn, AuraLunaEn, AuraOrionEn, plus CustomId(String).
• speaktostream(...) returns impl Stream<Item = bytes::Bytes>.

API reference (layered)

1. In-repo

- README.md - src/speak/rest.rs - src/speak/options.rs - examples/speak/rest/texttospeechtofile.rs - examples/speak/rest/texttospeechtostream.rs

1. OpenAPI

- Raw spec: https://developers.deepgram.com/openapi.yaml - Endpoint reference: https://developers.deepgram.com/reference/text-to-speech/speak-request

1. AsyncAPI

- Rust SDK support: not implemented in this crate - Raw spec if you need unsupported WS TTS: https://developers.deepgram.com/asyncapi.yaml

1. Context7

- /llmstxt/developersdeepgramllms_txt

1. Product docs

- https://developers.deepgram.com/docs/text-to-speech - https://developers.deepgram.com/docs/tts-rest

Gotchas

1. This crate is REST-only for TTS. There is no supported Rust WebSocket TTS surface in src/speak/ today.
2. Pick encoding/container pairs deliberately. For raw output use Container::None; for .wav output use Container::Wav.
3. speaktostream(...) still uses the REST endpoint. It streams HTTP response bytes; it is not the separate TTS WebSocket API.
4. Use API keys with Token. Do not send API keys as Bearer.

Example files in this repo

• examples/speak/rest/texttospeechtofile.rs
• examples/speak/rest/texttospeechtostream.rs

Central product skills

For cross-language Deepgram product knowledge — the consolidated API reference, documentation finder, focused runnable recipes, third-party integration examples, and MCP setup — install the central skills:

npx skills add deepgram/skills

This SDK ships language-idiomatic code skills; deepgram/skills ships cross-language product knowledge (see api, docs, recipes, examples, starters, setup-mcp).