--- type: "post" id: "gemini-3-8-tts-playground-analysis-e5135b" slug: "gemini-3-8-tts-playground-analysis-e5135b" title: "Gemini 3.8 TTS Playground" description: "Gemini 3.8 TTS turns multi-character speech from a production workaround into an API-level workflow component." retrieval_nugget: "Gemini 3.8 TTS turns multi-character speech from a production workaround into an API-level workflow component." published_at: "2026-09-24" updated_at: "2026-09-24" record_date: "2026-09-24" date_kind: "published_at" topics: [] source_urls: ["https://simonwillison.net/2026/Sep/23/gemini-tts-playground"] schema_version: "newruntime-agent-readable-v0.2" stable_id: "post:gemini-3-8-tts-playground-analysis-e5135b" status: "published" visuals: [] editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:5938f21ac741f50533cefb9dd0aac687508c31209368d1c6516a7ec0252d0445","reviewed_at":"2026-09-24T07:00:07.591Z","source_evidence_count":1,"verified_claim_count":4,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":4,"implication_count":2,"watch_condition_count":2,"related_record_count":0} analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Gemini 3.8 TTS turns multi-character speech from a production workaround into an API-level workflow component.","observed_facts":[{"text":"The source identifies two models: gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts.","source_urls":["https://simonwillison.net/2026/Sep/23/gemini-tts-playground"]},{"text":"The playground supports multi-speaker dialogue with per-speaker voices and delivery-style instructions.","source_urls":["https://simonwillison.net/2026/Sep/23/gemini-tts-playground"]},{"text":"The playground states that 2,089 voices are loaded.","source_urls":["https://simonwillison.net/2026/Sep/23/gemini-tts-playground"]},{"text":"The author reports that generating 1 minute 18 seconds of Flash TTS audio took about 20 seconds and cost 2.74 cents.","source_urls":["https://simonwillison.net/2026/Sep/23/gemini-tts-playground"]}],"mechanism":"The mechanism is structured composition: an application can represent dialogue as speakers, lines, voices, and style directives, then submit that structure to a TTS model instead of stitching individually generated clips together.","why_now":"Why now is that the source pairs this structured interface with an observed operating point: a 1 minute 18 second Flash TTS output reportedly took about 20 seconds and cost 2.74 cents.","implications":["The immediate implication is that teams can begin evaluating synthetic dialogue as a programmable runtime service, with cost and latency measured per produced scene rather than per isolated voice sample.","Multi-speaker TTS can move from bespoke audio assembly into agent-facing and automated media workflows."],"evidence_boundary":"The evidence boundary is important: these figures come from one author’s playground test, not a benchmark, service-level commitment, or independent quality evaluation.","watch_conditions":["Watch for whether the models retain distinct speaker identity and follow delivery instructions across longer, more complex dialogues.","Watch for published pricing, quota behavior, and safeguards around custom-voice creation."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied; this begins a distinct record on structured, multi-speaker TTS as a programmable workflow layer."} routes: {"html":"https://newruntime.com/posts/gemini-3-8-tts-playground-analysis-e5135b/","markdown":"https://newruntime.com/posts/gemini-3-8-tts-playground-analysis-e5135b.md","json":"https://newruntime.com/posts/gemini-3-8-tts-playground-analysis-e5135b.json"} editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]} --- # Gemini 3.8 TTS Playground ## Retrieval answer Gemini 3.8 TTS turns multi-character speech from a production workaround into an API-level workflow component. Gemini 3.8 TTS turns multi-character speech from a production workaround into an API-level workflow component. The public playground demonstrates an implementation-oriented reading of the release rather than a generic voice-model announcement. Simon Willison’s interface supports a cast of speakers, assigns each speaker a voice, and attaches a delivery-style instruction to each line. The page says that 2,089 voices are loaded, while the accompanying release description cited there says users can create a custom voice from a 30-second sample when they hold the relevant rights. The mechanism is structured composition: an application can represent dialogue as speakers, lines, voices, and style directives, then submit that structure to a TTS model instead of stitching individually generated clips together. That reduces orchestration work for conversational agents, narrated simulations, and automated media pipelines. Why now is that the source pairs this structured interface with an observed operating point: a 1 minute 18 second Flash TTS output reportedly took about 20 seconds and cost 2.74 cents. The immediate implication is that teams can begin evaluating synthetic dialogue as a programmable runtime service, with cost and latency measured per produced scene rather than per isolated voice sample. The evidence boundary is important: these figures come from one author’s playground test, not a benchmark, service-level commitment, or independent quality evaluation. Watch for whether the models retain distinct speaker identity and follow delivery instructions across longer, more complex dialogues. Source: https://simonwillison.net/2026/Sep/23/gemini-tts-playground Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json ## Continue in the graph Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`. - collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis. - collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph. - whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)