# \#tts **URL:** https://discuss.ai.google.dev/tag/tts/453.md [Latest](https://discuss.ai.google.dev/latest.md) · [Categories](https://discuss.ai.google.dev/categories.md) · [Tags](https://discuss.ai.google.dev/tags.md) --- ## [\[TTS Bug\] Voice consistency fails / Voice drift occurs every ~120 seconds in long audio generation (~10 min)](https://discuss.ai.google.dev/t/tts-bug-voice-consistency-fails-voice-drift-occurs-every-120-seconds-in-long-audio-generation-10-min/195216)
**Author:** [@CraftingFire](https://discuss.ai.google.dev/u/CraftingFire)\ **Replies:** 0\ **Last updated:** [October 26, 2026, 4:35am UTC](https://discuss.ai.google.dev/t/tts-bug-voice-consistency-fails-voice-drift-occurs-every-120-seconds-in-long-audio-generation-10-min/195216 "2026-10-26T04:35:10Z")
Summary When generating long-form audio (~10 minutes) in Single-Speaker TTS mode using an input prompt of ~9,580 characters, the voice fails to stay consistent. Every ~120 seconds (2 minutes), the voice noticeably shifts… --- ## [Voice Replication CreateVoice returns HTTP 500 with nested INVALID\_ARGUMENT for consent verification](https://discuss.ai.google.dev/t/voice-replication-createvoice-returns-http-500-with-nested-invalid-argument-for-consent-verification/195116)
**Author:** [@taka000825](https://discuss.ai.google.dev/u/taka000825)\ **Replies:** 0\ **Last updated:** [October 26, 2026, 4:10am UTC](https://discuss.ai.google.dev/t/voice-replication-createvoice-returns-http-500-with-nested-invalid-argument-for-consent-verification/195116 "2026-10-26T04:10:55Z")
Hello Gemini API team, We are investigating a Voice Replication CreateVoice validation failure. We have stopped making registration requests and are seeking guidance before any further submission. Endpoint/model: POST… --- ## [Commercial use and monetization of AI generated audio for YouTube](https://discuss.ai.google.dev/t/commercial-use-and-monetization-of-ai-generated-audio-for-youtube/195097)
**Author:** [@Yusef\_48](https://discuss.ai.google.dev/u/Yusef_48)\ **Replies:** 0\ **Last updated:** [October 26, 2026, 4:07am UTC](https://discuss.ai.google.dev/t/commercial-use-and-monetization-of-ai-generated-audio-for-youtube/195097 "2026-10-26T04:07:15Z")
Hello Google AI Studio Support Team, I create historical and educational videos for my YouTube channel. I would like to use AI-generated voices from Google AI Studio to narrate my original historical scripts. Could you… --- ## [Suspected copyright-filter false positive blocks verbatim Slovak legislative TTS (gemini-3.8-flash-tts, Batch API)](https://discuss.ai.google.dev/t/suspected-copyright-filter-false-positive-blocks-verbatim-slovak-legislative-tts-gemini-3-8-flash-tts-batch-api/188425)
**Author:** [@Peter\_P](https://discuss.ai.google.dev/u/Peter_P)\ **Replies:** 1\ **Last updated:** [October 23, 2026, 7:35am UTC](https://discuss.ai.google.dev/t/suspected-copyright-filter-false-positive-blocks-verbatim-slovak-legislative-tts-gemini-3-8-flash-tts-batch-api/188425 "2026-10-23T07:35:09Z")
Title: Suspected copyright-filter false positive blocks verbatim Slovak legislative TTS (gemini-3.8-flash-tts, Batch API) We are generating educational audio from user-supplied official Slovak driving-test / legislative… --- ## [Voice Replication rejects genuine human recordings as "synthetic speech or AI provenance watermarks" (ja-JP)](https://discuss.ai.google.dev/t/voice-replication-rejects-genuine-human-recordings-as-synthetic-speech-or-ai-provenance-watermarks-ja-jp/190598)
**Author:** [@vf-dev-jp](https://discuss.ai.google.dev/u/vf-dev-jp)\ **Replies:** 2\ **Last updated:** [October 23, 2026, 6:28am UTC](https://discuss.ai.google.dev/t/voice-replication-rejects-genuine-human-recordings-as-synthetic-speech-or-ai-provenance-watermarks-ja-jp/190598 "2026-10-23T06:28:52Z")
Hi team, We are getting a consistent rejection from Voice Replication for one speaker, and we believe it is a false positive. Setup Model: gemini-3.8-flash-tts Endpoint: POST /v1beta/voices (Gemini Developer API), st… --- ## [Gemini 3.8 Flash TTS: voice changes every ~500 input tokens on long text (internal chunking?)](https://discuss.ai.google.dev/t/gemini-3-8-flash-tts-voice-changes-every-500-input-tokens-on-long-text-internal-chunking/191419)
**Author:** [@Romeo\_Ilboudo](https://discuss.ai.google.dev/u/Romeo_Ilboudo)\ **Replies:** 0\ **Last updated:** [October 22, 2026, 4:27am UTC](https://discuss.ai.google.dev/t/gemini-3-8-flash-tts-voice-changes-every-500-input-tokens-on-long-text-internal-chunking/191419 "2026-10-22T04:27:15Z")
Hi, I generate long French narrations (10-20 min) with gemini-3.8-flash-tts, sending the whole script in a single request (AI Studio Interactions API and Vertex AI generateContent, same result). Problem: the voice (pit… --- ## [Gemini-3.8-flash-lite-tts stops early on batched text with \ tags while reporting completed / STOP (truncated audio is still billed)](https://discuss.ai.google.dev/t/gemini-3-8-flash-lite-tts-stops-early-on-batched-text-with-long-pause-tags-while-reporting-completed-stop-truncated-audio-is-still-billed/191142)
**Author:** [@takumi\_oda](https://discuss.ai.google.dev/u/takumi_oda)\ **Replies:** 2\ **Last updated:** [October 22, 2026, 12:29am UTC](https://discuss.ai.google.dev/t/gemini-3-8-flash-lite-tts-stops-early-on-batched-text-with-long-pause-tags-while-reporting-completed-stop-truncated-audio-is-still-billed/191142 "2026-10-22T00:29:25Z")
Hi everyone, and thank you for all the work on Gemini TTS. I would like to report an issue we have been seeing, in case it helps the team. What happens With gemini-3.8-flash-lite-tts, a single-speaker request containin… --- ## [Age Requirements clause: TTS-only use in a Discord bot, limited to age-restricted (18+) channels](https://discuss.ai.google.dev/t/age-requirements-clause-tts-only-use-in-a-discord-bot-limited-to-age-restricted-18-channels/190651)
**Author:** [@Bouz](https://discuss.ai.google.dev/u/Bouz)\ **Replies:** 1\ **Last updated:** [October 20, 2026, 3:18am UTC](https://discuss.ai.google.dev/t/age-requirements-clause-tts-only-use-in-a-discord-bot-limited-to-age-restricted-18-channels/190651 "2026-10-20T03:18:39Z")
Hello. We run DrazonChat, a Discord bot that translates chat messages between languages. Text translation uses a different provider. We would like to use gemini-3.8-flash-lite-tts on the paid tier to read translated mess… --- ## [Gemini 3.8 TTS / voice is a downgrade for personal-assistant and companion apps](https://discuss.ai.google.dev/t/gemini-3-8-tts-voice-is-a-downgrade-for-personal-assistant-and-companion-apps/184911)
**Author:** [@Ronsta](https://discuss.ai.google.dev/u/Ronsta)\ **Replies:** 4\ **Last updated:** [October 20, 2026, 12:01am UTC](https://discuss.ai.google.dev/t/gemini-3-8-tts-voice-is-a-downgrade-for-personal-assistant-and-companion-apps/184911 "2026-10-20T00:01:55Z")
Title: Gemini 3.8 TTS / voice is a downgrade for personal-assistant and companion apps I build two voice products on Gemini: a personal assistant and a companion app. Both run on the Aoede voice with carefully tuned pro… --- ## [Replicated voice created in AI Studio Playground disappeared a few hours after it appeared (gemini-3.8-flash-tts)](https://discuss.ai.google.dev/t/replicated-voice-created-in-ai-studio-playground-disappeared-a-few-hours-after-it-appeared-gemini-3-8-flash-tts/190785)
**Author:** [@Peat\_Tiravi](https://discuss.ai.google.dev/u/Peat_Tiravi)\ **Replies:** 0\ **Last updated:** [October 19, 2026, 12:14pm UTC](https://discuss.ai.google.dev/t/replicated-voice-created-in-ai-studio-playground-disappeared-a-few-hours-after-it-appeared-gemini-3-8-flash-tts/190785 "2026-10-19T12:14:15Z")
Hi AI Studio team, My replicated voice disappeared from Google AI Studio a few hours after it first showed up. What I did: 1. Opened the Playground (Generate speech) with model gemini-3.8-flash-tts. 2. Clicked “Create ne… --- ## [Allowlist request – Gemini Live API replicated voice (replicated\_voice\_config) on Agent Platform, project joyachat](https://discuss.ai.google.dev/t/allowlist-request-gemini-live-api-replicated-voice-replicated-voice-config-on-agent-platform-project-joyachat/190563)
**Author:** [@Social1](https://discuss.ai.google.dev/u/Social1)\ **Replies:** 0\ **Last updated:** [October 19, 2026, 2:13am UTC](https://discuss.ai.google.dev/t/allowlist-request-gemini-live-api-replicated-voice-replicated-voice-config-on-agent-platform-project-joyachat/190563 "2026-10-19T02:13:19Z")
Hello, we’d like to request allowlisting for the replicated voice feature in the Gemini Live API on Gemini Enterprise Agent Platform (Vertex AI) for project joyachat (region us-central1, model gemini-3.8-live). Our setu… --- ## [Gemini 3.8 Flash TTS sometimes adds unscripted speech and long silences](https://discuss.ai.google.dev/t/gemini-3-8-flash-tts-sometimes-adds-unscripted-speech-and-long-silences/190222)
**Author:** [@RobbieBowman](https://discuss.ai.google.dev/u/RobbieBowman)\ **Replies:** 0\ **Last updated:** [October 18, 2026, 12:47am UTC](https://discuss.ai.google.dev/t/gemini-3-8-flash-tts-sometimes-adds-unscripted-speech-and-long-silences/190222 "2026-10-18T00:47:28Z")
Example responseId: kRTUat-ULr-AytMPw\_Cu6A Model: gemini-3.8-flash-tts Request started: 2026-10-18T00:36:33.578Z (UTC) HTTP status: 200 finishReason: STOP Returned 152.68 seconds of audio, including approximately 12… --- ## [Is it allowed to use Gemini TTS output for speaker inversion in another TTS model?](https://discuss.ai.google.dev/t/is-it-allowed-to-use-gemini-tts-output-for-speaker-inversion-in-another-tts-model/188338)
**Author:** [@coffee\_tree](https://discuss.ai.google.dev/u/coffee_tree)\ **Replies:** 2\ **Last updated:** [October 16, 2026, 2:12pm UTC](https://discuss.ai.google.dev/t/is-it-allowed-to-use-gemini-tts-output-for-speaker-inversion-in-another-tts-model/188338 "2026-10-16T14:12:21Z")
I have a question about the permitted use of audio generated by Gemini TTS. I am currently using \`gemini-2.5-flash-preview-tts\` with the Erinome preset voice, and I understand that this is currently a preview model. I … --- ## [Problem with my Voice Replication](https://discuss.ai.google.dev/t/problem-with-my-voice-replication/189941)
**Author:** [@Bounheng\_Southichak](https://discuss.ai.google.dev/u/Bounheng_Southichak)\ **Replies:** 0\ **Last updated:** [October 16, 2026, 9:46am UTC](https://discuss.ai.google.dev/t/problem-with-my-voice-replication/189941 "2026-10-16T09:46:37Z")
Dear all, once I tried to create a voice replication on Google AI studio, speech generation, but everytime it showed up with the following message (see attachment). Please help me solve this problem. --- ## [Voice Design (Gemini TTS): are fictional child characters supported? Minimum age, and approved path](https://discuss.ai.google.dev/t/voice-design-gemini-tts-are-fictional-child-characters-supported-minimum-age-and-approved-path/188899)
**Author:** [@Ricardo\_Garcia](https://discuss.ai.google.dev/u/Ricardo_Garcia)\ **Replies:** 1\ **Last updated:** [October 16, 2026, 5:22am UTC](https://discuss.ai.google.dev/t/voice-design-gemini-tts-are-fictional-child-characters-supported-minimum-age-and-approved-path/188899 "2026-10-16T05:22:58Z")
Hi all, We produce a scripted fiction micro-series in Spanish (El Salvador) on Vertex AI (project microserie-ia). Some scenes include fictional child characters (ages 8 to 11) with one short, harmless line each, for exa… --- ## [Gemini-3.8-flash-tts keeps re-reading the text when the input contains a repeated paragraph (up to 10 min of loops + 10 min of silence, all billed)](https://discuss.ai.google.dev/t/gemini-3-8-flash-tts-keeps-re-reading-the-text-when-the-input-contains-a-repeated-paragraph-up-to-10-min-of-loops-10-min-of-silence-all-billed/188536)
**Author:** [@linger20202](https://discuss.ai.google.dev/u/linger20202)\ **Replies:** 1\ **Last updated:** [October 15, 2026, 7:52am UTC](https://discuss.ai.google.dev/t/gemini-3-8-flash-tts-keeps-re-reading-the-text-when-the-input-contains-a-repeated-paragraph-up-to-10-min-of-loops-10-min-of-silence-all-billed/188536 "2026-10-15T07:52:25Z")
Model: gemini-3.8-flash-tts API: Gemini API (AI Studio key), models/gemini-3.8-flash-tts:streamGenerateContent?alt=sse. Also seen on Vertex AI (reached through Vercel AI Gateway), and once on the Interactions API path. D… --- ## [Gemini TTS — post-processing output and cloning our own Voice Design voice](https://discuss.ai.google.dev/t/gemini-tts-post-processing-output-and-cloning-our-own-voice-design-voice/189583)
**Author:** [@Frentezo](https://discuss.ai.google.dev/u/Frentezo)\ **Replies:** 0\ **Last updated:** [October 15, 2026, 7:03am UTC](https://discuss.ai.google.dev/t/gemini-tts-post-processing-output-and-cloning-our-own-voice-design-voice/189583 "2026-10-15T07:03:13Z")
Hello, I build a personal voice assistant on the Gemini API (paid tier, Gemini 3.8 Flash-Lite TTS). Its voice was created with Voice Design from a text prompt, so it is fully synthetic and is not based on any real perso… --- ## [Terms clarification: Gemini TTS audio generated offline for an Android game restricted to adults](https://discuss.ai.google.dev/t/terms-clarification-gemini-tts-audio-generated-offline-for-an-android-game-restricted-to-adults/188821)
**Author:** [@kimtaegwan](https://discuss.ai.google.dev/u/kimtaegwan)\ **Replies:** 1\ **Last updated:** [October 15, 2026, 2:57am UTC](https://discuss.ai.google.dev/t/terms-clarification-gemini-tts-audio-generated-offline-for-an-android-game-restricted-to-adults/188821 "2026-10-15T02:57:15Z")
Hello, I am developing a Korean-language Android visual novel game and would like clarification about the Gemini API Additional Terms of Service. I am considering using Gemini TTS to generate prerecorded voice lines fo… --- ## [Gemini TTS in AI Studio consistently skips the same line in a ~1 page (~470 words) input, reproducible on every run](https://discuss.ai.google.dev/t/gemini-tts-in-ai-studio-consistently-skips-the-same-line-in-a-1-page-470-words-input-reproducible-on-every-run/189115)
**Author:** [@KawsarSheikh](https://discuss.ai.google.dev/u/KawsarSheikh)\ **Replies:** 0\ **Last updated:** [October 14, 2026, 6:43am UTC](https://discuss.ai.google.dev/t/gemini-tts-in-ai-studio-consistently-skips-the-same-line-in-a-1-page-470-words-input-reproducible-on-every-run/189115 "2026-10-14T06:43:05Z")
Hi /Assalamu alaykum everyone, I’m using the Gemini TTS model in Google AI Studio to generate voiceovers. Each time I paste a script of about one Google Docs page (~470 words) into the input. The generated audio skips a… --- ## [Gemini-3.8-flash-tts: intermittent low metallic hum in the background of some generations](https://discuss.ai.google.dev/t/gemini-3-8-flash-tts-intermittent-low-metallic-hum-in-the-background-of-some-generations/187177)
**Author:** [@Matthieu\_Grambert](https://discuss.ai.google.dev/u/Matthieu_Grambert)\ **Replies:** 1\ **Last updated:** [October 13, 2026, 10:42am UTC](https://discuss.ai.google.dev/t/gemini-3-8-flash-tts-intermittent-low-metallic-hum-in-the-background-of-some-generations/187177 "2026-10-13T10:42:07Z")
Hi, We use gemini-3.8-flash-tts (streamGenerateContent, responseModalities AUDIO, prebuilt voices, 24 kHz PCM16 mono) to voice museum audio-guide narrations of about 50 seconds, in 12 languages. Some generations contai… --- ## [Will Tier 2 increase the effective daily quota for Gemini 3.8 TTS?](https://discuss.ai.google.dev/t/will-tier-2-increase-the-effective-daily-quota-for-gemini-3-8-tts/187071)
**Author:** [@Taerin\_TTS](https://discuss.ai.google.dev/u/Taerin_TTS)\ **Replies:** 2\ **Last updated:** [October 12, 2026, 3:44pm UTC](https://discuss.ai.google.dev/t/will-tier-2-increase-the-effective-daily-quota-for-gemini-3-8-tts/187071 "2026-10-12T15:44:59Z")
Hi Google team, I currently use the paid Tier 1 Gemini API for Korean narrative videos and want to confirm the effective daily quotas for gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts before spending more to qualif… --- ## [Gemini-2.5-pro-tts deprecation clarifications](https://discuss.ai.google.dev/t/gemini-2-5-pro-tts-deprecation-clarifications/187500)
**Author:** [@Daniele\_Morotti](https://discuss.ai.google.dev/u/Daniele_Morotti)\ **Replies:** 0\ **Last updated:** [October 8, 2026, 7:40am UTC](https://discuss.ai.google.dev/t/gemini-2-5-pro-tts-deprecation-clarifications/187500 "2026-10-08T07:40:43Z")
Hi, while reading https://ai.google.dev/gemini-api/docs/deprecations?hl=en#audio-models, I noticed that it says the Gemini 2.5 Pro and Flash Preview TTS models will be made unavailable starting November 17. The problem … --- ## [Gemini TTS Bug Report: \`speech\_metadata.style\` Fails to Apply Character Acting & Vocal Styling in Gemini 3.8 TTS](https://discuss.ai.google.dev/t/gemini-tts-bug-report-speech-metadata-style-fails-to-apply-character-acting-vocal-styling-in-gemini-3-8-tts/186799)
**Author:** [@mariusa](https://discuss.ai.google.dev/u/mariusa)\ **Replies:** 1\ **Last updated:** [October 8, 2026, 4:05am UTC](https://discuss.ai.google.dev/t/gemini-tts-bug-report-speech-metadata-style-fails-to-apply-character-acting-vocal-styling-in-gemini-3-8-tts/186799 "2026-10-08T04:05:42Z")
Target Services / Models: gemini-3.8-flash-lite-tts gemini-3.8-flash-tts (Compared against baseline: gemini-3.1-flash-tts-preview) SDK / API: @google/genai (Node.js / REST API) Date: October 2026 Severity: Functional… --- ## [Gemini 2.5 Pro TTS has regressed — frequent micro-cuts and broken phonemes make it unusable](https://discuss.ai.google.dev/t/gemini-2-5-pro-tts-has-regressed-frequent-micro-cuts-and-broken-phonemes-make-it-unusable/187369)
**Author:** [@OMAN](https://discuss.ai.google.dev/u/OMAN)\ **Replies:** 0\ **Last updated:** [October 7, 2026, 4:57pm UTC](https://discuss.ai.google.dev/t/gemini-2-5-pro-tts-has-regressed-frequent-micro-cuts-and-broken-phonemes-make-it-unusable/187369 "2026-10-07T16:57:02Z")
I am reporting a serious audio quality regression in Gemini 2.5 Pro TTS. I have been using this model extensively for scripted narration and dialogue generation, and the current behavior is clearly different from how th… --- ## [How were the prebuilt Gemini TTS voices (Puck, Charon, ...) created? Any official page?](https://discuss.ai.google.dev/t/how-were-the-prebuilt-gemini-tts-voices-puck-charon-created-any-official-page/187196)
**Author:** [@Lounis\_Yapa](https://discuss.ai.google.dev/u/Lounis_Yapa)\ **Replies:** 0\ **Last updated:** [October 6, 2026, 9:11pm UTC](https://discuss.ai.google.dev/t/how-were-the-prebuilt-gemini-tts-voices-puck-charon-created-any-official-page/187196 "2026-10-06T21:11:06Z")
Hello, I use gemini-3.8-flash-tts with the prebuilt voices Puck and Charon to narrate short animated videos. The documentation lists the prebuilt voices but does not say how they were made. Is there an official page th… --- ## [Tier 2 upgrade stuck after meeting requirements – Gemini 3.8 Flash TTS blocked at 102/100 RPD](https://discuss.ai.google.dev/t/tier-2-upgrade-stuck-after-meeting-requirements-gemini-3-8-flash-tts-blocked-at-102-100-rpd/187008)
**Author:** [@taka\_taka](https://discuss.ai.google.dev/u/taka_taka)\ **Replies:** 1\ **Last updated:** [October 6, 2026, 11:00am UTC](https://discuss.ai.google.dev/t/tier-2-upgrade-stuck-after-meeting-requirements-gemini-3-8-flash-tts-blocked-at-102-100-rpd/187008 "2026-10-06T11:00:25Z")
Hi Google Gemini API team, My Gemini API project appears to be stuck on Paid Tier 1 even though I have fully met the Tier 2 requirements. Current situation: Billing: Prepaid Cumulative successful payment: over USD $1… --- ## [Gemini API age restriction — may static TTS audio, generated offline by an adult, ship inside a children's learning app?](https://discuss.ai.google.dev/t/gemini-api-age-restriction-may-static-tts-audio-generated-offline-by-an-adult-ship-inside-a-childrens-learning-app/186036)
**Author:** [@Geochinbong-i](https://discuss.ai.google.dev/u/Geochinbong-i)\ **Replies:** 1\ **Last updated:** [October 5, 2026, 10:48am UTC](https://discuss.ai.google.dev/t/gemini-api-age-restriction-may-static-tts-audio-generated-offline-by-an-adult-ship-inside-a-childrens-learning-app/186036 "2026-10-05T10:48:32Z")
Hello, I’m building a small learning app for children aged 4–9 (Korean literacy and early math). The first version is used only within my own family; a public release may come later. I’d like to use gemini-3.8-flash-tt… --- ## [When will the quality degradation of Gemini 2.5 TTS Pro be corrected?](https://discuss.ai.google.dev/t/when-will-the-quality-degradation-of-gemini-2-5-tts-pro-be-corrected/186106)
**Author:** [@JL\_Garcia](https://discuss.ai.google.dev/u/JL_Garcia)\ **Replies:** 1\ **Last updated:** [October 5, 2026, 9:45am UTC](https://discuss.ai.google.dev/t/when-will-the-quality-degradation-of-gemini-2-5-tts-pro-be-corrected/186106 "2026-10-05T09:45:35Z")
I haven’t been able to work on my project for over two weeks, which requires generating audio with a British accent. Until now, I’ve only been using Gemini 2.5 Pro TTS, which I consider to be the best model currently ava… --- ## [Tier 2 project still enforcing Tier 1 daily quota (100 RPD) on Gemini 3.8 TTS models](https://discuss.ai.google.dev/t/tier-2-project-still-enforcing-tier-1-daily-quota-100-rpd-on-gemini-3-8-tts-models/186987)
**Author:** [@Sound\_Gloox](https://discuss.ai.google.dev/u/Sound_Gloox)\ **Replies:** 0\ **Last updated:** [October 5, 2026, 9:30am UTC](https://discuss.ai.google.dev/t/tier-2-project-still-enforcing-tier-1-daily-quota-100-rpd-on-gemini-3-8-tts-models/186987 "2026-10-05T09:30:38Z")
Hi team, Our project was upgraded to Tier 2, but the API still enforces the Tier 1 daily request quota on the TTS models. Project: Default Gemini Project (gen-lang-client-022828…) Billing: Tier 2 · Prepay (shown in AI… --- ## [Voice replication (POST /v1beta/voices) always returns 404 "Requested entity was not found" — normal TTS works](https://discuss.ai.google.dev/t/voice-replication-post-v1beta-voices-always-returns-404-requested-entity-was-not-found-normal-tts-works/186902)
**Author:** [@nozatan](https://discuss.ai.google.dev/u/nozatan)\ **Replies:** 1\ **Last updated:** [October 5, 2026, 4:53am UTC](https://discuss.ai.google.dev/t/voice-replication-post-v1beta-voices-always-returns-404-requested-entity-was-not-found-normal-tts-works/186902 "2026-10-05T04:53:30Z")
Hi, I’m trying voice replication with gemini-3.8-flash-tts following https://ai.google.dev/gemini-api/docs/voice-replication, but creating a voice always fails with: 404 NOT\_FOUND “Requested entity was not found.” Nor… [Next page](https://discuss.ai.google.dev/tag/tts/453.md?match_all_tags=true&page=1&tags%5B%5D=tts)