Multilingual Text to Speech

Turn text to spoken audio by selecting a model based on the language of the text.

Requirements

installed speeches service
installed models specified in speeches service

Quickstart

Click Add custom model button in speeches service.

In model ID, write the name of your model e.g. my-model.

Set default model ID (this model will be used when there are no matching language model pairs).

Example model ID: speaches-ai/piper-en_US-ryan-medium

Set ISO 639-1 language codes and model IDs in next rows.

Supported languages codes:

af, ar, bg, bn, ca, cs, cy, da, de, el, en, es, et, fa, fi, fr, gu, he, hi, hr, hu, id, it, ja, kn, ko, lt, lv, mk, ml, mr, ne, nl, no, pa, pl, pt, ro, ru, sk, sl, so, sq, sv, sw, ta, te, th, tl, tr, uk, ur, vi, zh-cn, zh-tw

Example model ID: speaches-ai/piper-en_US-ryan-medium

Example Setup

window with speeches-ai custom model

Example request in english language:

curl -X POST \
 "https://deepfellow-server-host/v1/audio/speech" \
  -H "Authorization: Bearer DEEPFELLOW-PROJECT-API-KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "my-model",
    "input": "Today is a wonderful day to build something people love!",
  }' \
  --output speech.mp3

from pathlib import Path
from openai import OpenAI

client = OpenAI(
    base_url="https://deepfellow-server-host/v1",
    api_key="DEEPFELLOW-PROJECT-API-KEY" 
)
speech_file_path = Path(__file__).parent / "speech.mp3"

with client.audio.speech.with_streaming_response.create(
    model="my-model",
    input="Today is a wonderful day to build something people love!",
) as response:
    response.stream_to_file(speech_file_path)

import * as fs from 'fs';
import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: 'https://deepfellow-server-host/v1',
    apiKey: 'DEEPFELLOW-PROJECT-API-KEY' 
});

const response = await client.audio.speech.create({
    model: 'my-model',
    input: 'Today is a wonderful day to build something people love!',
});

const buffer = Buffer.from(await response.arrayBuffer());
await fs.promises.writeFile('speech.mp3', buffer);

Example request in polish language:

curl -X POST \
 "https://deepfellow-server-host/v1/audio/speech" \
  -H "Authorization: Bearer DEEPFELLOW-PROJECT-API-KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "my-model",
    "input": "Dzisiaj jest wspaniały dzień na stworzenie czegoś, co ludzie kochają!",
  }' \
  --output speech.mp3

from pathlib import Path
from openai import OpenAI

client = OpenAI(
    base_url="https://deepfellow-server-host/v1",
    api_key="DEEPFELLOW-PROJECT-API-KEY" 
)
speech_file_path = Path(__file__).parent / "speech.mp3"

with client.audio.speech.with_streaming_response.create(
    model="my-model",
    input="Dzisiaj jest wspaniały dzień na stworzenie czegoś, co ludzie kochają!",
) as response:
    response.stream_to_file(speech_file_path)

import * as fs from 'fs';
import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: 'https://deepfellow-server-host/v1',
    apiKey: 'DEEPFELLOW-PROJECT-API-KEY' 
});

const response = await client.audio.speech.create({
    model: 'my-model',
    input: 'Dzisiaj jest wspaniały dzień na stworzenie czegoś, co ludzie kochają!',
});

const buffer = Buffer.from(await response.arrayBuffer());
await fs.promises.writeFile('speech.mp3', buffer);

Multilingual Text to Speech

Requirements

Quickstart

Example Setup

On this page