Cartesia Voice Cloning API + MCP vs Soniox Voice Cloning

Cartesia Voice Cloning API + MCP

Instant clones from 10 seconds of audio, up to 60 seconds used on Sonic 3.6. No consent or speaker verification in the clone API.

Soniox Voice Cloning

One API call and a clip of up to 2 minutes. No consent capture or speaker verification, and the terms say so.

Cartesia Voice Cloning API + MCP

1. Send Cartesia-Version on every call. The clone endpoint lists it as a required header
2. Pass the speaker's recorded language. A clone is built from one language, add others with the accents API
3. Keep IVC uploads under 16 MB
4. Don't blind-retry POST /voices/clone. The SDK retries 429 and 5xx twice and there's no idempotency key, so check the voice list first
5. Poll a Pro clone fine-tune until it finishes before using the voice ID

Soniox Voice Cloning

1. Poll the voice until the target model's status is ready before using it in TTS
2. On voice_not_prepared call recompute, don't retry the TTS request
3. Don't retry voice_failed even though it's a 503. Create a new voice from a better clip
4. Use a key from the project that owns the voice, voices are per project
5. Keep the clip under 2 minutes and 35 MB, longer fails with voice_audio_too_long