API Plan Finder
가격과 한도는 공급사 공식 페이지와 같습니다확인 2026-11-16English

OpenAI: 공식 페이지가 정하지 않은 것

86 of 98 conditions we check across 2 listed plans are not stated on OpenAI's own pages, so a verdict on them is unknown. Each line says what one official sentence would have to state. Checked against the official pages as of 2026-11-16.

Cheapest alternatives to OpenAI at three monthly volumes

tts-1

OpenAI Text to Speech · 조건 49개 중 43개가 정해지지 않음

이 요금제의 판정: 월 1,000,000자 (텍스트).

tts-1-hd

OpenAI Text to Speech · 조건 49개 중 43개가 정해지지 않음

이 요금제의 판정: 월 1,000,000자 (텍스트).

공식 페이지에 적힌 것

65 sentences from OpenAI's own pages, each with its page and the date we read it. They are shown as written and are not part of any verdict.

OpenAI (all plans) 20개 적힘
  • Abuse monitoring prompt logging: Yes (abuse monitoring logs may contain customer content such as prompts and responses, unless excluded under Zero Data Retention or Modified Abuse Monitoring)
    Abuse monitoring logs may contain certain customer content, such as prompts and responses
    developers.openai.com/api/docs/guides/your-data.md · 확인 2026-11-09
  • API 인증 방식: api_key (HTTP bearer), short-lived access tokens from workload identity federation
    The OpenAI API accepts bearer credentials from API keys or from short-lived access tokens created with [workload identity federation]
    developers.openai.com/api/reference/overview.md · 확인 2026-11-09
  • Backward compatibility: OpenAI avoids breaking changes in major API versions whenever reasonably possible: REST API v1, first-party client libraries (semantic versioning), model families
    OpenAI provides stability to API users by avoiding breaking changes in major API versions whenever reasonably possible.
    developers.openai.com/api/reference/overview.md · 확인 2026-11-09
  • Data residency eligibility: eligible organizations can enable data residency when creating a project in the API Platform
    Eligible organizations can enable data residency when creating a project in the API Platform.
    developers.openai.com/api/docs/guides/data-residency.md · 확인 2026-11-16
  • Data residency excluded: data residency does not cover transfers caused by the end user's or customer's infrastructure location, third-party products or content offered through the services, or non-customer data
    Data residency does not apply to: 1. Any transmission or storage of Customer Content outside of the selected region caused by the location of an End User or Customer’s infrastructure when accessing the services. 2. Products, services, or content offered by parties other than OpenAI through the Services. 3. Any data other than Customer Content, such as system data.
    developers.openai.com/api/docs/guides/data-residency.md · 확인 2026-11-16
  • Data residency fee: uplift pct: 10 (data residency endpoints, for models released on or after March 5, 2026 that are eligible for data residency)
    Data residency endpoints are charged a [10% uplift](https://developers.openai.com/api/docs/pricing) for models released on or after March 5, 2026, that are eligible for data residency.
    developers.openai.com/api/docs/guides/data-residency.md · 확인 2026-11-16
  • Discontinuation notice exclusions: preview models (identified by 'preview' in the model name) may be retired with much shorter notice, such as 2 weeks
    may be retired with much shorter notice, such as 2 weeks
    developers.openai.com/api/docs/deprecations.md · 확인 2026-11-09
  • Discontinuation notice months: 6 (generally available models; unless safety or compliance concerns require a faster timeline)
    - **Generally available models:** At least 6 months.
    developers.openai.com/api/docs/deprecations.md · 확인 2026-11-09
  • HIPAA BAA: available: Yes (customers who executed an OpenAI Business Associate and Healthcare Addendum and are provisioned with Private Retention with Private Safety Processing can use BAA-eligible endpoints for PHI; /v1/audio/speech is not eligible for Private Retention with PSP)
    For customers who have executed an OpenAI Business Associate and Healthcare Addendum, once your org ID is provisioned with Private Retention with Private Safety Processing, BAA-eligible endpoints can be used for processing PHI, even if data is retained.
    developers.openai.com/api/docs/guides/your-data.md · 확인 2026-11-09
  • 사람의 고객 내용 검토: under Safety Retention, content the classifiers flag as potentially violating may be retained and human reviewed; under Private Retention with PSP, retained content is excluded from human review unless required by law
    we may retain and human review customer content when using these models that our classifiers detect as potentially violating
    developers.openai.com/api/docs/guides/your-data.md · 확인 2026-11-09
  • Impersonation prohibited: 예
    Don’t impersonate others or violate our
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Mcp scope: documentation-only: read-only access to OpenAI developer documentation (search and page content); does not call the OpenAI API
    This MCP server is documentation-only. It does not call the OpenAI API on your
    developers.openai.com/learn/docs-mcp.md · 확인 2026-11-09
  • 지역별 주소: us.api.openai.com, eu.api.openai.com, au.api.openai.com, ca.api.openai.com, jp.api.openai.com, in.api.openai.com, sg.api.openai.com, kr.api.openai.com, gb.api.openai.com, ae.api.openai.com
    Use that project's API key with the regional domain prefix listed in the table below, such as eu.api.openai.com for Europe.
    developers.openai.com/api/docs/guides/data-residency.md · 확인 2026-11-16
  • 지역 처리 선택 방식: per request via the regional domain prefix with an API key from a Global project that has per-request data residency enabled (alternative to a region-specific project)
    Use an API key from that Global project with a regional domain prefix for each request that needs regional processing.
    developers.openai.com/api/docs/guides/data-residency.md · 확인 2026-11-16
  • Reserved capacity: Yes (in some cases, dedicated capacity can be provisioned for continued access after a model's shutdown date; contact sales)
    In some cases, developers may be able to provision dedicated capacity for continued access after a model's shutdown date.
    developers.openai.com/api/docs/deprecations.md · 확인 2026-11-09
  • Residency processing outside region: Yes (when the selected region does not support regional processing, content may be processed and temporarily stored outside it)
    If your selected Region does not support regional processing, as identified below, OpenAI may also process and temporarily store Customer Content outside of the Region to deliver the services.
    developers.openai.com/api/docs/guides/data-residency.md · 확인 2026-11-16
  • SDK 언어: javascript, python, go, java, csharp, ruby (official client libraries; Speech examples also show curl and the openai CLI)
    Install an official client library from the [libraries page]
    developers.openai.com/api/reference/overview.md · 확인 2026-11-09
  • Service change notice: on a model deprecation, customers actively using the model are notified by email and the deprecation is documented on the deprecations page
    we notify customers who are actively using the model by email and document the deprecation on this page
    developers.openai.com/api/docs/deprecations.md · 확인 2026-11-09
  • ZDR 켜는 방식: after approval, set in Settings > Organization > Data controls > Data Retention, for the whole organization or per project (default, Zero Data Retention, Modified Abuse Monitoring or None)
    From that tab, you can configure data retention controls at both the organization and project level.
    developers.openai.com/api/docs/guides/your-data.md · 확인 2026-11-09
  • Zdr scope: OpenAI may make models ineligible for ZDR or MAM for specific customers, notified in advance in writing (Private Retention with PSP; Safety Retention when needed to investigate or prevent severe risk activity)
    we reserve the right to make models ineligible for Zero Data Retention or Modified Abuse Monitoring for specific customers
    developers.openai.com/api/docs/guides/your-data.md · 확인 2026-11-09
tts-1 4개 적힘
tts-1-hd 3개 적힘
OpenAI Text to Speech 38개 적힘
  • AI 사용 표시 필요: 예
    to provide a clear disclosure to end users that the TTS voice they are hearing
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • Api key restrictions: api.voices.read to read consent phrases and use a custom voice, api.voices.write plus custom-voice API access to create consents and voices, project-scoped API key, same project for every request
    creating consents and voices requires `api.voices.write` and
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • 청구 단위: characters (tts-1 and tts-1-hd are priced per 1M characters; gpt-4o-mini-tts per 1M text input tokens and audio output tokens)
    Pricing is based on the number of tokens used, or other metrics based on the model type.
    developers.openai.com/api/docs/models/tts-1.md · 확인 2026-11-09
  • Builtin voices: count: 13
    The TTS endpoint provides 13 built‑in voices to control how speech is rendered from text.
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • Clone consent statement required: Yes (a separate consent recording in which the voice actor reads one of the fixed consent phrases; any divergence from the script fails)
    **Consent recording:** This recording captures the voice actor providing consent to create a likeness of their voice.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Clone sample formats: mpeg, wav, ogg, aac, flac, webm, mp4
    The audio samples must be one of the following types: `mpeg`, `wav`, `ogg`, `aac`, `flac`, `webm`, or `mp4`.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Clone sample max file size: 10 MiB per upload
    Each upload is limited to 10 MiB.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • 복제 샘플 초: max: 60 (audio samples for voices created from recordings)
    The audio samples must be 60 seconds or less.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Cloned voice supported apis: GPT-Live, Text to Speech API, Realtime API, Chat Completions API with audio output
    These voices can be used with GPT-Live, the [Text to Speech API]
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Custom voice accents: English accents (gpt-live-1 custom voices; accent set in session.instructions)
    `gpt-live-1` supports custom voices with English accents.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Custom voice synthesis model: gpt-realtime-2.1-mini with the Realtime API (voice ID set in session.audio.output.voice)
    Use `gpt-realtime-2.1-mini` with the [Realtime API](https://developers.openai.com/api/docs/guides/realtime) to generate speech in your custom voice.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Custom voice usage rate: speech in a prompt-generated voice is billed at regular GPT-Live session rates; listening to a voice in the Playground also runs a GPT-Live session billed as a regular session
    Using it to generate speech in GPT-Live is billed at regular session rates.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • 맞춤 목소리 최대 수: 20 (voices created from recordings, per organization)
    At most 20 voices from recordings can be created per organization.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Dated model snapshots: Yes (gpt-4o-mini-tts: default snapshot gpt-4o-mini-tts-2025-12-15; also gpt-4o-mini-tts-2025-03-20)
    Default snapshot: `gpt-4o-mini-tts-2025-12-15`
    developers.openai.com/api/docs/models/gpt-4o-mini-tts.md · 확인 2026-11-09
  • Designed voice supported apis: GPT-Live (not supported by the Text to Speech, Realtime or Chat Completions APIs)
    voices work with GPT-Live. They aren't supported by the Text to Speech,
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • 감정 조절: Yes (gpt-4o-mini-tts, through prompts: accent, emotional range, intonation, impressions, speed of speech, tone, whispering)
    `gpt-4o-mini-tts` lets you use prompts to control these aspects of speech:
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • Language quality tier: voices are currently optimized for English
    Voices are currently optimized for English.
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • Legacy access until shutdown: Yes (existing integrations can use the Speech API workflows until shutdown (January 6, 2027))
    Existing integrations can use the Speech API workflows shown below until
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • 요청당 최대 입력: amount: 2,000; unit: tokens (gpt-4o-mini-tts)
    The maximum number of input tokens is 2000.
    developers.openai.com/api/docs/models/gpt-4o-mini-tts.md · 확인 2026-11-09
  • 모델 API 제공: gpt-realtime-2.1-mini is not a supported model for /v1/audio/speech; migration is a change of API workflow to the Realtime API
    `gpt-realtime-2.1-mini` isn't a supported model for `/v1/audio/speech`.
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • 출력 형식: mp3, opus, aac, flac, wav, pcm
    - **MP3**: The default response format for general use cases. - **Opus**: For internet streaming and communication, low latency. - **AAC**: For digital audio compression, preferred by YouTube, Android, iOS. - **FLAC**: For lossless audio compression, favored by audio enthusiasts for archiving. - **WAV**: Uncompressed WAV audio, suitable for low-latency applications to avoid decoding overhead. - *…
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • 결과물이 고유하지 않음: 예
    **Voices aren’t guaranteed to be unique.**
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • 가격 방식: usage-based: price per characters (tts-1, tts-1-hd) or per tokens (gpt-4o-mini-tts)
    Pricing is based on the number of tokens used, or other metrics based on the model type.
    developers.openai.com/api/docs/models/tts-1.md · 확인 2026-11-09
  • Rate limit model: limits set by usage tier; the tier (and so the limits) increases automatically as more requests are sent and more is spent on the API
    Your usage tier determines how high these limits are set and automatically increases as you send more requests and spend more on the API.
    developers.openai.com/api/docs/models/tts-1.md · 확인 2026-11-09
  • Recommended replacement: gpt-realtime-2.1-mini (Realtime API)
    | **Jan 6, 2027** | `gpt-4o-mini-tts`, `gpt-4o-mini-tts-2025-03-20`, `gpt-4o-mini-tts-2025-12-15` | Deprecated | `gpt-realtime-2.1-mini` | Oct 1, 2026 |
    developers.openai.com/api/docs/deprecations.md · 확인 2026-11-16
  • 샘플링 주파수(Hz): 24,000 (PCM output: raw samples, 16-bit signed, little-endian, without header (page says 24kHz))
    **PCM**: Similar to WAV but contains the raw samples in 24kHz (16-bit signed, low-endian), without the header.
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • Supplemental product terms: Text-to-Speech Supplemental Agreement applies to custom voices from recordings
    Refer to the Text-to-Speech Supplemental Agreement for additional terms of use.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • 지원 언어: 57: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, … +45 more (the TTS model generally follows Whisper's language support; voices are optimized for English)
    Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian…
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • 대상 용도: narrate a written blog post, produce spoken audio in multiple languages, give realtime audio output using streaming
    - Produce spoken audio in multiple languages
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • 음성 합성 모델: tts-1, tts-1-hd, gpt-4o-mini-tts
    The `tts-1`, `tts-1-hd`, and `gpt-4o-mini-tts` models are deprecated and will
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • 목소리 복제 API: 예
    Voices from recordings must be created through an API request.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Voice cloning eligibility: eligible customers only; contact sales; once enabled for the organization the Voices tab under Audio is available
    Custom voices created from recordings are limited to eligible customers.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • 목소리 설계: Yes (prompt-to-voice is generally available to all API customers; prompt-generated voices work with GPT-Live only)
    Prompt-to-voice is generally available to all API customers.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Voice design candidates: 1
    It doesn't include audio or a preview
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Voice design fee usd: USD 0
    Creating a prompt-generated voice is free.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • 목소리 주인 동의 필요: the consent recording and the reference sample must come from the same person (the sample voice must match the consent recording); a mismatched speaker is rejected
    The consent recording and reference sample must come from the same person.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09
  • Web playground: OpenAI.fm interactive demo for trying the voices and the latest text-to-speech model
    Hear and play with these voices in [OpenAI.fm](https://openai.fm), our interactive demo
    developers.openai.com/api/docs/guides/text-to-speech.md · 확인 2026-11-09
  • ZDR 제외 데이터: voice creation through /v1/audio/voices, including creation from recordings, is not compatible with Zero Data Retention
    Voice creation through `/v1/audio/voices`, including creation from recordings, isn't compatible with Zero Data Retention.
    developers.openai.com/api/docs/guides/custom-voices.md · 확인 2026-11-09

정정 보내기

If one of these is already stated on a page we missed, or a sentence has changed, send the page address through https://github.com/scraping-api-plans/web-data-plan-finder/issues. Nothing is sent to OpenAI from this page.