Beta
Clone an Arabic voice without losing its regional character
Keep the voice private
A clone belongs to the account that created it. Publishing a voice is a separate, explicit decision rather than the default.
Use one voice across Arabic text
Select your saved voice in the studio, or pass its voice ID to the speech API to generate new recordings.
Make consent part of the workflow
The cloning flow requires confirmation that the speaker owns the voice or gave permission for it to be cloned.
A short path from sample to speech
Create a voice in the dashboard by uploading a recording and confirming that you own the voice or have the speaker’s permission. Once encoding finishes, use the resulting voice ID with the speech endpoint.
- 01
Record a clean sample
Use 10 to under 30 seconds of one speaker with little background noise and no music.
- 02
Confirm permission and create
Name the voice, confirm the speaker's consent, and let the platform encode the sample.
- 03
Generate with the new voice
Select the clone in the dashboard or pass its voice id to POST /v1/audio/speech.
How Arabic voice cloning works
For projects that need voice cloning, Arabic speech generation is a straightforward three-step process. You submit a short reference audio file, confirm that you have the speaker's permission, and then use the resulting voice ID with our OpenAI-compatible API to generate streaming audio.
curl -X POST "https://api.sawtakarabi.ai/v1/voices" \
-H "Authorization: Bearer <API_KEY>" \
-F "name=Custom Voice" \
-F 'labels={"dialect":"saudi-najdi"}' \
-F "files=@reference_audio.wav"Available anywhere via API
Use your cloned voice ID in any speech synthesis request just like the built-in voices. Pass the new ID to the POST /v1/audio/speech endpoint to generate streaming audio instantly.
Stream native Arabic speech
The synthesized audio retains the original dialect and pronunciation characteristics. Your custom voice streams uncompressed PCM audio exactly like the standard catalogue, allowing for real-time playback.
Manage your private voices
Keep track of your cloned voices directly from the dashboard. Your voice remains private to your account and requires explicit scope permissions for API access, ensuring complete control over its usage.
Consent is built in, not bolted on
Sawtak Arabi requires the explicit consent of the voice owner before any clone can be created. This strict requirement ensures that commercial teams can build applications on a legally and ethically sound foundation, avoiding the risks associated with unauthorized voice generation while maintaining absolute trust with their users.
A clone that speaks your dialect
Cloned voices retain their original regional identity rather than flattening into a generic accent. By assigning a dialect label during creation, your custom voice seamlessly joins our library of over 90 Arabic dialect varieties, ensuring the generated speech sounds authentic and culturally aligned with your target audience.
Practical applications for cloned voices
Private cloned voices allow developers and creators to maintain brand consistency and personalize user experiences across multiple audio touchpoints. From marketing materials to assistive applications, a localized voice helps you connect more deeply with Arabic-speaking users without relying on standard accents.
Branded content
Produce consistent marketing materials, podcasts, and automated videos using a recognizable voice that belongs entirely to your brand.
Assistive voice
Power custom voice agents, smart assistants, and IVR systems with an Arabic voice that feels familiar, localized, and welcoming to callers.
Media localization
Streamline dubbing pipelines by generating translated audio tracks using the original speaker's cloned voice, preserving both the dialect and the original delivery style.
Personal projects
Use your own cloned voice to narrate long-form articles, create audiobooks, or experiment with custom text-to-speech workflows in your specific dialect.