Speech Generation

Available Models

The full list of models can be viewed on the Models page or retrieved dynamically via API endpoints: https://openai.bothub.chat/v1/models and https://bothub.chat/api/v2/replicate/v1/models

BotHub supports speech generation via an OpenAI-compatible API. You can convert text to audio, select a voice, audio file format, and playback speed.

Speech generation uses the Text-to-Speech (TTS) family of models:

• tts-1 — standard model with low latency
• tts-1-hd — improved model with higher audio quality

---

Available Voices

When generating speech, you can choose one of the built-in voices: alloy, echo, fable, onyx, nova, shimmer.

---

Supported Audio Formats

The API supports audio generation in several formats: mp3, opus, aac, flac.

---

Main Request Parameters

The following parameters are used when creating audio:

Parameter	Type	Description
model	string	Speech generation model (tts-1 or tts-1-hd)
voice	string	Voice for speech synthesis
input	string	Text to convert to speech
response_format	string	Output audio format
speed	number	Playback speed (0.25 – 4.0)

---

Speech Generation Example

JS

import OpenAI from 'openai';
import fs from 'fs';

const openai = new OpenAI({
  apiKey: 'YOUR_BOTHUB_API_KEY',
  baseURL: 'https://openai.bothub.chat/v1'
});

async function main() {
  const response = await openai.audio.speech.create({
    model: 'tts-1-hd',
    voice: 'nova',
    input: 'Hello! This is an example of speech generation via BotHub.',
    response_format: 'mp3',
    speed: 0.9
  });

  const buffer = Buffer.from(await response.arrayBuffer());

  await fs.promises.writeFile('output.mp3', buffer);

  console.log('Audio file saved successfully.');
}

main();

Python

from pathlib import Path
from openai import OpenAI

client = OpenAI(
    api_key='YOUR_BOTHUB_API_KEY',
    base_url='https://openai.bothub.chat/v1'
)

speech_file_path = Path(__file__).parent / "output.mp3"

response = client.audio.speech.create(
    model='tts-1-hd',
    voice='nova',
    input='Hello! This is an example of speech generation via BotHub.',
    response_format='mp3',
    speed=0.9
)

response.stream_to_file(speech_file_path)

print('Audio file saved successfully.')

Go

package main

import (
	"context"
	"fmt"
	"io"
	"os"

	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	client := openai.NewClient(
		option.WithAPIKey("YOUR_BOTHUB_API_KEY"),
		option.WithBaseURL("https://openai.bothub.chat/v1"),
	)

	response, err := client.Audio.Speech.New(context.Background(), openai.AudioSpeechNewParams{
		Model:          openai.SpeechModel("tts-1-hd"),
		Voice:          "nova",
		Input:          "Hello! This is an example of speech generation via BotHub.",
		ResponseFormat: openai.AudioSpeechNewParamsResponseFormatMP3,
		Speed:          openai.Float(0.9),
	})
	if err != nil {
		panic(err)
	}
	defer response.Body.Close()

	file, err := os.Create("output.mp3")
	if err != nil {
		panic(err)
	}
	defer file.Close()

	if _, err := io.Copy(file, response.Body); err != nil {
		panic(err)
	}

	fmt.Println("Audio file saved successfully.")
}

cURL

curl https://openai.bothub.chat/v1/audio/speech \
  -H "Authorization: Bearer YOUR_BOTHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1-hd",
    "voice": "nova",
    "input": "Hello! This is an example of speech generation via BotHub.",
    "response_format": "mp3",
    "speed": 0.9
  }' \
  --output output.mp3

---

Recommendations

Usage Recommendations

• For most scenarios, it is recommended to use tts-1 if generation speed is important.
• Use tts-1-hd if audio quality is the priority.
• The mp3 format is suitable for most applications and provides a good balance between quality and file size.
• A speed value greater than 1.0 accelerates playback, while a value below 1.0 makes the speech slower and smoother.

Official OpenAI Documentation

You can read more about the Text-to-Speech API in the official OpenAI documentation:

https://developers.openai.com/api/docs/guides/text-to-speech