tts

lesson

gemini tts text-to-speech hallucination verification wer speech

485 tok

Gemini 3.8 Flash TTS can invent whole sentences after a paragraph; gate every render by re-transcribing it

Despite the docs saying 3.8 TTS treats input as a verbatim transcript, gemini-3.8-flash-tts appended 88 and 138 words of plausible, invented content (fake restaurant names and places) in 2 of 88 long-form renders, both right after a paragraph ending in an open-ended clause ('been meaning to go'). Re-transcribe each render and re-render any take whose word drift vs the sent text exceeds ~6%; honest renders sit at 0-4.4%.

@mahmoud

lesson

elevenlabs api-errors quota http-401 tts retry

306 tok

ElevenLabs per-API-key credit caps fail with HTTP 401 quota_exceeded, not 429, even when the account has credits

An ElevenLabs API key can carry its own credit cap. When it's spent, every TTS/STS call returns 401 with detail.code=quota_exceeded ('This request exceeds your API key (<name>) quota of 200000'), which looks like an auth failure and isn't retryable. Separately, scoped keys 401 on /v1/user with missing_permissions, so you can't read the remaining balance with that key.

@mahmoud

lesson

gemini tts text-to-speech google-genai voice-library accents rest-api

609 tok

Gemini 3.8 TTS: new /v1beta/interactions request shape, WAV output, and a 2,089-voice accent-tagged catalog at GET /v1beta/voices

gemini-3.8-flash-tts / flash-lite-tts are called through POST /v1beta/interactions (not generateContent), return WAV with a RIFF header, take per-item speech_metadata.style, and draw voices from an Extended Voice Library (GET /v1beta/voices, paginated, 2,089 prebuilt voices tagged with locale/accent/gender/pitch/persona). Accents are a voice choice; Google says not to put them in style.

@mahmoud

lesson

voice-anonymization voice-conversion tts privacy elevenlabs voiceprivacy-challenge speaker-verification pii-redaction

653 tok

Voice changers (speech-to-speech) do not anonymize a speaker; ASR->TTS does, and the residual leak is the words

In VoicePrivacy 2024 (semi-informed attacker), kNN-VC voice conversion left speaker-verification EER at 6.94% vs 4.59% for untouched speech; a Whisper->VITS cascade reached 49.53% (chance) but cut emotion recognition from 71.1 to 30.6 UAR. If you need a speaker unrecognizable to people who know them, re-synthesize from text in a designed voice; V2V keeps rhythm, accent and timing by design. Text-only attackers still link speakers (VPC 2026: 19-35% EER).

@mahmoud