---
type: "post"
id: "openai-s-custom-voices-documentation-describes-prompt-to-dd276d"
slug: "openai-s-custom-voices-documentation-describes-prompt-to-dd276d"
title: "OpenAI’s custom-voices documentation describes prompt-to-voice as generally available to API customers"
description: "OpenAI’s custom-voices guide makes voice identity a configurable resource in its API stack, but not yet a universal one."
retrieval_nugget: "OpenAI’s custom-voices guide makes voice identity a configurable resource in its API stack, but not yet a universal one."
published_at: "2026-10-16"
updated_at: "2026-10-16"
record_date: "2026-10-16"
date_kind: "published_at"
topics: ["api-design","generative-media","multimodal"]
source_urls: ["https://developers.openai.com/api/docs/guides/custom-voices"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:openai-s-custom-voices-documentation-describes-prompt-to-dd276d"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:6198b4a4fd90f3ea1167e64e8cbe41a3a0d806c80598b4da736e8e99816482ba","reviewed_at":"2026-10-16T20:11:23.635Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":1,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Voice customization is becoming an application-level asset, while product boundaries still determine where that asset can run.","observed_facts":[{"text":"The guide says prompt-to-voice is generally available to API customers and that a prompt-generated voice can be created and saved without a reference recording.","source_urls":["https://developers.openai.com/api/docs/guides/custom-voices"]},{"text":"These generated voices work with GPT-Live, but not with the Text to Speech, Realtime, or Chat Completions APIs; the guide also specifies a limit of 100 such voices per organization.","source_urls":["https://developers.openai.com/api/docs/guides/custom-voices"]},{"text":"OpenAI added nine preset voices created with native-speaking actors in French, German, Hindi, Japanese, and Korean.","source_urls":["https://developers.openai.com/api/docs/guides/custom-voices"]}],"mechanism":"A description is turned into a reusable saved voice, decoupling voice selection from a one-off speech-generation request, while API compatibility remains the deployment constraint.","why_now":"OpenAI has also added nine preset voices made with native-speaking actors across French, German, Hindi, Japanese, and Korean, making voice choice more relevant to teams shipping multilingual interfaces.","implications":["Builders should treat voice selection as a GPT-Live-specific design and integration decision, not assume a voice can move across all audio APIs."],"evidence_boundary":"The public guide documents supported workflows and policy requirements; it does not establish usage, quality, or performance outcomes.","watch_conditions":["Watch for documentation that extends prompt-generated voices to additional APIs or changes the 100-voice organizational limit."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied for this specific combination of prompt-generated voices, API restrictions, and new international presets."}
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"]}
routes: {"html":"https://newruntime.com/posts/openai-s-custom-voices-documentation-describes-prompt-to-dd276d/","markdown":"https://newruntime.com/posts/openai-s-custom-voices-documentation-describes-prompt-to-dd276d.md","json":"https://newruntime.com/posts/openai-s-custom-voices-documentation-describes-prompt-to-dd276d.json"}
---

# OpenAI’s custom-voices documentation describes prompt-to-voice as generally available to API customers

## Retrieval answer

OpenAI’s custom-voices guide makes voice identity a configurable resource in its API stack, but not yet a universal one.

OpenAI’s custom-voices guide makes voice identity a configurable resource in its API stack, but not yet a universal one. **Thesis:** Voice customization is becoming an application-level asset, while product boundaries still determine where that asset can run.

**Observed facts:** The guide says prompt-to-voice is generally available to API customers and that a prompt-generated voice can be created and saved without a reference recording. **Observed facts:** These generated voices work with GPT-Live, but not with the Text to Speech, Realtime, or Chat Completions APIs; the guide also specifies a limit of 100 such voices per organization. **Mechanism:** A description is turned into a reusable saved voice, decoupling voice selection from a one-off speech-generation request, while API compatibility remains the deployment constraint.

**Why now:** OpenAI has also added nine preset voices made with native-speaking actors across French, German, Hindi, Japanese, and Korean, making voice choice more relevant to teams shipping multilingual interfaces. **First implication:** Builders should treat voice selection as a GPT-Live-specific design and integration decision, not assume a voice can move across all audio APIs. The guide further requires adult voices, transparency that speech is AI-generated, and preservation of provenance signals. **Evidence boundary:** The public guide documents supported workflows and policy requirements; it does not establish usage, quality, or performance outcomes. **First watch condition:** Watch for documentation that extends prompt-generated voices to additional APIs or changes the 100-voice organizational limit.

This starts a distinct analytical record because no prior New Runtime record was supplied for this specific combination of prompt-generated voices, API restrictions, and new international presets.

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`.

- topic hub: [Api Design](https://newruntime.com/topics/api-design.md): Explore the api-design topic hub.
- topic hub: [Generative Media](https://newruntime.com/topics/generative-media.md): Explore the generative-media topic hub.
- topic hub: [Multimodal](https://newruntime.com/topics/multimodal.md): Explore the multimodal topic hub.
- 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)