ElevenLabs Text to Speech API + MCP vs Soniox Text-to-Speech

ElevenLabs Text to Speech API + MCP

Keys can be limited to chosen endpoints and given a credit quota, and service accounts hold keys that don't belong to a person. Content may be used for training unless you opt out under Data use, and the opt-out only applies going forward.

Soniox Text-to-Speech

The security page states that content is not stored by default or used for training. Audio output is capped at two minutes per request or stream.

ElevenLabs Text to Speech API + MCP

1. Call Eleven v4 through Text to Dialogue, not /v1/text-to-speech.
2. Spell out numbers yourself on eleven_flash_v2_5, which doesn't normalise them by default, and turning that on is Enterprise only.
3. On 429 read code, back off on rate_limit_exceeded and wait for running requests on concurrent_limit_exceeded.
4. Keep each request under 10,000 characters on v4 and Multilingual v2, 5,000 on v3.
5. Give the agent a key scoped to Text to Speech with a credit quota.

Soniox Text-to-Speech

1. Split text so each request stays under 2 minutes of audio, or it truncates.
2. Branch on error_type, not the message, and back off on limit_exceeded.
3. Use a temporary API key for browser clients.
4. Use bracketed audio tags such as [whispering] instead of SSML.
5. Pick the regional host (EU, Japan, India) that matches your data residency.