Skip to main content
TTS in production

​
Make your first voice with Spitch

Start buildingView Endpoints
Sample integrationWorks in prod
from spitch import Spitch

client = Spitch(api_key="YOUR-API-KEY")

audio = client.speech.synthesize(
    voice="amina",
    text="Welcome to Spitch. Let's build something remarkable.",
    format="mp3",
    style="conversational",
)

with open("welcome.mp3", "wb") as output:
    output.write(audio.content)

​
Get started in minutes

Follow the onboarding flow our teams use in production to ship your first transcription or voice experience quickly.

1

​
Request access & generate your key

Log in to the Spitch dashboard to create a workspace, invite teammates, and manage usage.

Open dashboard2

​
Connect an SDK or hit the REST API

Install the official Python or TypeScript clients in your app, or make direct HTTP calls with curl.

Browse libraries3

​
Configure models & launch to production

Tune vocabularies, manage files, and orchestrate jobs with webhooks, retries, and monitoring.

Explore advanced guides

​
SDK quickstart

Make your first transcription call using the official clients or the REST API.

Quickstart guide
from spitch import Spitch

client = Spitch(api_key="YOUR-API-KEY")
response = client.speech.transcribe(
    content=open("sample.wav", "rb"),
    language="en",
    model="mansa_v1",
)

print(response.text)

​
Platform capabilities

Assemble voice and language features with consistent APIs, streaming support, and low-latency infrastructure across the continent.

Speech-to-Text

Convert audio streams or files to text with custom vocabularies, timestamps, and speaker diarization.

Text-to-Speech

Generate natural voices tuned to African tonal patterns for IVRs, narrators, and conversational agents.

Language Translation

Translate bidirectionally between English and African languages with contextual awareness.

Tone Marking

Add accurate diacritical marks to Yoruba text programmatically for clarity and pronunciation.

​
Build for your use case

Follow step-by-step guides to ship production experiences fast, whether you are embedding transcription or designing full voice agents.

Audio transcription app

Build a web tool that ingests audio files and returns transcripts with timestamps in seconds.

Multilingual chatbot

Combine speech, translation, and TTS to power rich conversational agents in multiple languages.

Voice agent blueprint

Orchestrate realtime voice flows with LiveKit, event webhooks, and Spitch’s streaming APIs.

Platform operations

Manage batch jobs, retry policies, and monitoring to keep your production workloads healthy.

​
Operate with confidence

Understand pricing, service coverage, and the operational levers that help teams in regulated industries launch safely.

Model catalog

Choose streaming or batch models with the right accuracy and latency profile for your use case.

File storage

Upload, manage, and reuse audio assets securely across teams from a single dashboard.

Languages & pricing

Explore coverage, supported dialects, and pricing so you can forecast launches with confidence.

Voices catalog

Pick from curated voices or request custom voice training for your brand identity.

Keys & auth

Implement secure API key management across environments and rotate credentials programmatically.

Troubleshooting

Diagnose common issues quickly with guidance on logging, monitoring, and best practices.

​
Need a tailored integration?

Chat with our solutions team for architecture reviews, custom voice creation, or migration support.

Join the communityTalk to support