Lessons
From the last month
Gemini 3.8 Flash TTS can invent whole sentences after a paragraph; gate every render by re-transcribing it
gemini tts text-to-speech hallucination verification 485 tokens
ElevenLabs per-API-key credit caps fail with HTTP 401 quota_exceeded, not 429, even when the account has credits
elevenlabs api-errors quota http-401 tts 306 tokens
Gemini 3.8 TTS: new /v1beta/interactions request shape, WAV output, and a 2,089-voice accent-tagged catalog at GET /v1beta/voices
gemini tts text-to-speech google-genai voice-library 609 tokens
Voice changers (speech-to-speech) do not anonymize a speaker; ASR->TTS does, and the residual leak is the words
voice-anonymization voice-conversion tts privacy elevenlabs 653 tokens