Skip to main content
Also known as text-to-speech (TTS), speech generation/synthesis is an integral part of modern AI systems. We have built this endpoint with strong support across many languages. Spitch offers production-ready voices across English, Hausa, Igbo, Yoruba, Amharic, and Nigerian Pidgin so you can choose accents and styles that match your audience.

​
Request

The generate() function can be used to generate speech. The following parameters are available:

​
Parameters

  • text (required) - The text you want to convert to speech
  • voice (required) - Voice ID to use for generation
  • language (optional) - ISO 639 language code to use for generation
  • speed (optional) - Voice speed from 0.7 to 1.2; defaults to 1.0
  • format (optional) - Output audio format, defaults to wav

​
Audio Formats

The format parameter supports the following audio formats:
  • wav (default) - Standard wave format
  • mp3 - MPEG Layer III audio
  • ogg_opus - OGG container with Opus codec
  • webm_opus - WebM container with Opus codec
  • flac - Free Lossless Audio Codec
  • pcm_s16le - Raw PCM 16-bit little-endian
  • mulaw - μ-law encoded audio
  • alaw - A-law encoded audio
Examples are provided below as a guide for you.
Need guidance on tone, punctuation, or narration style? Run through the TTS Prompting Guide for playbooks, checklists, and review workflows.

​
Response

The response for speech generation is streamed audio bytes.
  • The Content-Type is audio/wav
  • The content is streamed back to the caller.
  • The file type of the generated audio is wav. If you use the streaming interface (Python SDK), you can start to take action on the byte chunks, e.g. stream to file.

​
Choosing a Voice

Browse the roster on the Voices page and match voices to your use case before generating audio.

​
Examples

import os
from spitch import Spitch

os.environ["SPITCH_API_KEY"] = "YOUR_API_KEY"
client = Spitch()

with open("new.mp3", "wb") as f:
    response = client.speech.generate(
        text="Bawo ni ololufe mi?",
        language="yo",
        voice="sade",
        speed=1.0,
        format="mp3"
    )
    f.write(response.read())
For error codes and retry guidance, see Troubleshooting.