API Plan Finder
Prices and limits match the providers' official pagesChecked 2026-11-16

Text-to-speech plans compared

54 text-to-speech plans from 15 providers, checked 2026-11-16 against the official pages. 260 features compared, 240 read from official pages by our pipeline, 0 measured by us.

Price statistics for text to speech · No audio has been made yet, so the listening slots and measured figures below are empty and say so.

Choose what to compare

Plans (2 to 6; now 4)
Cartesia
Deepgram
ElevenLabs
Fish
Google
Gradium
Inworld
Lemonfox.ai
MiniMax
Murf
OpenAI
Amazon
Rime
SpeechifyAI
Typecast

Listen to the same sentence

Same sentence, every plan: choose a language and a sentence, press play on each plan. Plans without a sample say so.

Your order #48213 ships on March 15, 2026 at 2:30 PM.

14 of 15 products name English on their official page

Side by side

260 features compared, 240 read from official pages by our pipeline, 0 measured by us. Open a cell's source to see the official sentence, its page and the date we read it. A cell that says "not stated on the pages we read" is not a no.

Price and billing 3 rows
FeatureElevenLabs CreatorOpenAI tts-1-hdGoogle Cloud Chirp 3: HD voicesAmazon Web Services Neural voices
Monthly cost at 1,000,000 charactersfrom $18.33; the rest is not stated on the pages we read
howNeeds 1,000,000 characters; the plan includes 275,000 and the extra-usage terms are not stated on the official page. · 2026-11-16
$30.00
how1,000,000 characters = 1,000,000 characters × $0.03 per 1,000 → $30/month. · 2026-11-16
$0.00
how1,000,000 characters = 1,000,000 characters × $0.03 per 1,000, minus the $30 monthly credit → $0/month. · 2026-11-16
$16.00
how1,000,000 characters = 1,000,000 characters × $0.016 per 1,000 → $16/month. · 2026-11-16
Billingannual subscriptionpay as you gopay as you gopay as you go
Price per 1,000 charactersnot stated on the pages we read$0.03
source
tts-1-hd | Text | $30.00 / 1M characters | - | -
developers.openai.com/api/docs/pricing.md · checked 2026-11-16
$0.03
source
Chirp 3: HD voices (sku:F977-2280-6F1B) 0 to 1 million characters US$0.00003 per character
cloud.google.com/text-to-speech/pricing · checked 2026-11-16
$0.016
source
Amazon Polly’s Neural voices are priced at $16.00 per 1 million characters for speech or Speech Marks requested (when outside the free tier).
aws.amazon.com/polly/pricing · checked 2026-11-16
Limits 1 rows
FeatureElevenLabs CreatorOpenAI tts-1-hdGoogle Cloud Chirp 3: HD voicesAmazon Web Services Neural voices
Included each month275,000 characters
source
$0.08 ~$0.08/minute 275,000 ~275 min
elevenlabs.io/pricing/api · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Features (judged by the engine) 48 rows
FeatureElevenLabs CreatorOpenAI tts-1-hdGoogle Cloud Chirp 3: HD voicesAmazon Web Services Neural voices
Commercial use of the audioYes
source
if you access or use our Services free of charge (such a user, a “ Free User ”), you may only use the Services for non-commercial purposes; (ii) if you access or use our Services through a paid subscription plan (such a user, a “ Paid User ”), you may use the Services for commercial purposes
elevenlabs.io/terms-of-use · checked 2026-11-16
not stated on the pages we readYes
source
You can use the audio data files you create using Cloud Text-to-Speech in your applications or media in compliance with the Google Cloud Platform Terms of Service
cloud.google.com/text-to-speech/quotas · checked 2026-11-16
Yes
source
As between you and AWS, your Polly output belongs to you.
aws.amazon.com/polly/faqs · checked 2026-11-16
Voice cloningYes
source
Everything in free, plus Commercial License Instant Voice Cloning
elevenlabs.io/pricing/api · checked 2026-11-16
not stated on the pages we read
source
Custom voices created from recordings are limited to eligible customers.
developers.openai.com/api/docs/guides/custom-voic… · checked 2026-11-16
not stated on the pages we read
source
Important: Access to Instant Custom Voice is restricted to allow-listed users.
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-16
not stated on the pages we read
source
How do I get started with Amazon Polly Brand Voice? If you are interested in building a Brand Voice using Amazon Polly, please reach out to your AWS Account Manager or contact us for more information.
aws.amazon.com/polly/faqs · checked 2026-11-16
Streaming audioYes
source
The Text-to-Speech WebSockets API is designed to generate audio from partial text input while ensuring consistency throughout the generated audio.
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-16
Yes
source
This means the audio can be played before the full file is generated and made accessible.
developers.openai.com/api/docs/guides/text-to-spe… · checked 2026-11-16
Yes
source
Streaming Cloud Text-to-Speech is only compatible with Chirp 3: HD voices
cloud.google.com/text-to-speech/docs/create-audio… · checked 2026-11-16
not stated on the pages we read
KoreanYes
source
Korean (ko)
elevenlabs.io/docs/overview/models.md · checked 2026-11-16
Yes
source
Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian
developers.openai.com/api/docs/guides/text-to-spe… · checked 2026-11-16
Yes
source
Korean (South Korea) Premium ko-KR ko-KR-Chirp3-HD-Achernar FEMALE
cloud.google.com/text-to-speech/docs/list-voices-… · checked 2026-11-16
Yes
source
Japanese ja-JP Korean ko-KR Norwegian nb-NO
docs.aws.amazon.com/polly/latest/dg/supported-lan… · checked 2026-11-16
Your text is not used to train modelsnot stated on the pages we read
source
you may opt out of our use of your Content for training at any time by navigating to the 'Data use' menu in the 'Terms and Privacy' section of your ElevenLabs account.
elevenlabs.io/terms-of-use · checked 2026-11-16
Yes
source
data sent to the OpenAI API is not used to train or improve OpenAI models (unless you explicitly opt in to share data with us).
developers.openai.com/api/docs/guides/your-data.md · checked 2026-11-16
not stated on the pages we read
source
Streaming Cloud Text-to-Speech is only compatible with Chirp 3: HD voices
cloud.google.com/text-to-speech/docs/create-audio… · checked 2026-11-16
not stated on the pages we read
source
Amazon Polly may store and use text inputs processed by the service solely to provide and maintain the service and to improve and develop the quality of Amazon Polly and other Amazon machine-learning/artificial-intelligence technologies.
aws.amazon.com/polly/faqs · checked 2026-11-16
Free allowance that repeats every monthnot stated on the pages we readnot stated on the pages we readYes
source
Chirp 3: HD voices (sku:F977-2280-6F1B) 0 to 1 million characters US$0.00003 per character
cloud.google.com/text-to-speech/pricing · checked 2026-11-16
not stated on the pages we read
source
For Neural voices, the free tier includes 1 million characters per month for speech or Speech Marks requests, for the first 12 months.
aws.amazon.com/polly/pricing · checked 2026-11-16
Official MCP serverYes
source
The ElevenLabs hosted MCP server is a remote
elevenlabs.io/docs/eleven-agents/operate/hosted-m… · checked 2026-11-16
Yes
source
Server URL (streamable HTTP):** `https://developers.openai.com/mcp`
developers.openai.com/learn/docs-mcp.md · checked 2026-11-16
not stated on the pages we read
source
Streaming Cloud Text-to-Speech is only compatible with Chirp 3: HD voices
cloud.google.com/text-to-speech/docs/create-audio… · checked 2026-11-16
not stated on the pages we read
source
As between you and AWS, your Polly output belongs to you.
aws.amazon.com/polly/faqs · checked 2026-11-16
Remote MCP serverYes
source
The ElevenLabs hosted MCP server is a remote
elevenlabs.io/docs/eleven-agents/operate/hosted-m… · checked 2026-11-16
Yes
source
Server URL (streamable HTTP):** `https://developers.openai.com/mcp`
developers.openai.com/learn/docs-mcp.md · checked 2026-11-16
not stated on the pages we read
source
Streaming Cloud Text-to-Speech is only compatible with Chirp 3: HD voices
cloud.google.com/text-to-speech/docs/create-audio… · checked 2026-11-16
not stated on the pages we read
source
As between you and AWS, your Polly output belongs to you.
aws.amazon.com/polly/faqs · checked 2026-11-16
MCP sign-in method statedYes
source
Authentication uses OAuth. When you connect, you sign in with your ElevenLabs account and grant the assistant scoped access to your workspace.
elevenlabs.io/docs/eleven-agents/operate/hosted-m… · checked 2026-11-16
not stated on the pages we read
source
Server URL (streamable HTTP):** `https://developers.openai.com/mcp`
developers.openai.com/learn/docs-mcp.md · checked 2026-11-16
not stated on the pages we read
source
Streaming Cloud Text-to-Speech is only compatible with Chirp 3: HD voices
cloud.google.com/text-to-speech/docs/create-audio… · checked 2026-11-16
not stated on the pages we read
source
As between you and AWS, your Polly output belongs to you.
aws.amazon.com/polly/faqs · checked 2026-11-16
SOC 2 reportYes
source
SOC 2 compliance
elevenlabs.io/pricing/api · checked 2026-11-16
not stated on the pages we readYes
source
for standards such as ISO 27001, ISO 27017, ISO 27018, SOC 2, SOC 3, and PCI DSS.
docs.cloud.google.com/document-ai/docs/security · checked 2026-11-16
Yes
source
AWS SOC 2 Security, Availability, Confidentiality, & Privacy Report available to AWS customers from AWS Artifact .
aws.amazon.com/compliance/soc-faqs · checked 2026-11-16
Data region statednot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Data processing agreementYes
source
Custom terms & assurance around DPA/SLAs
elevenlabs.io/pricing/api · checked 2026-11-16
not stated on the pages we readYes
source
"Cloud Data Processing Addendum" means the
cloud.google.com/terms · checked 2026-11-16
Yes
source
These Service Terms incorporate the AWS Data Processing Addendum (“DPA”), when you use AWS Services to process Customer Data (as defined in the DPA).
aws.amazon.com/service-terms · checked 2026-11-16
Uptime SLAnot stated on the pages we readnot stated on the pages we readYes
source
(i) For GCP Services, each of the then-current service level agreements at
cloud.google.com/terms · checked 2026-11-16
not stated on the pages we read
Pronunciation dictionaryYes
source
Create a pronunciation dictionary from rules
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-16
not stated on the pages we readYes
source
Custom pronunciations is available across all locales except: bn-IN , gu-IN ,
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-16
Yes
source
You can modify the pronunciation of particular words, such as company names, acronyms, foreign words and neologisms
aws.amazon.com/polly/faqs · checked 2026-11-16
Cancel at any timeYes
source
You can cancel your subscription at any time.
elevenlabs.io/pricing/api · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readYes
source
You may terminate this Agreement for any reason by providing us notice and closing your account for all Services for which we provide an account closing mechanism.
aws.amazon.com/agreement · checked 2026-11-16
You own the text you sendYes
source
you retain all rights in and to your Input.
elevenlabs.io/terms-of-use · checked 2026-11-16
not stated on the pages we readYes
source
property. As between the parties, Customer retains all
cloud.google.com/terms · checked 2026-11-16
Yes
source
You always retain ownership of your content and we will only use your content with your consent.
aws.amazon.com/polly/faqs · checked 2026-11-16
You own the generated audioYes
source
you retain all rights in and to your Output.
elevenlabs.io/terms-of-use · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readYes
source
As between you and AWS, your Polly output belongs to you.
aws.amazon.com/polly/faqs · checked 2026-11-16
Word timestampsnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Voice designYes
source
Design a voice
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Emotion controlnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
On-premises deploymentnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Priority supportYes
source
Priority support
elevenlabs.io/pricing/api · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Training opt-outYes
source
you may opt out of our use of your Content for training at any time by navigating to the 'Data use' menu
elevenlabs.io/terms-of-use · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Organizations and teamsnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Access until period end after cancellingnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Long-form synthesisYes
source
Most stable on long-form generations
elevenlabs.io/docs/overview/models.md · checked 2026-11-16
not stated on the pages we readYes
source
Cloud TTS API, which supports streaming and long-form text.
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-16
not stated on the pages we read
Pause controlnot stated on the pages we readnot stated on the pages we readYes
source
Pause control is available across all locales.
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-16
not stated on the pages we read
Language parameterYes
source
Language code (ISO 639-1) used to enforce a language for the model and text normalization.
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Shared credit poolnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Data deleted with the accountYes
source
All data is deleted from our systems permanently when you delete your account.
elevenlabs.io/docs/eleven-api/resources/zero-rete… · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readYes
source
Following closure of your AWS account, we will delete Your Content in accordance with the technical documentation applicable to the Services.
aws.amazon.com/service-terms · checked 2026-11-16
Quota increase on requestnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Nonverbal tagsYes
source
Audio tags for fine-grained control
elevenlabs.io/pricing/api · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Volume discountYes
source
Significant discounts at scale
elevenlabs.io/pricing/api · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Dedicated support channelnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Several contexts on one WebSocketYes
source
WSS Multi-Context WebSocket
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Browser access tokensYes
source
These tokens are valid for a limited time and can be used to connect to the API without exposing your API key, for example from the client side.
elevenlabs.io/docs/api-reference/authentication · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
GDPR compliantnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
SSMLYes
source
enable_ssml_parsing boolean Optional Defaults to false
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-16
not stated on the pages we readNo
source
Chirp 3: HD voices doesn't support SSML input, speaking rate and pitch-audio parameters, and the A-Law audio encoding.
cloud.google.com/text-to-speech/docs/list-voices-… · checked 2026-11-16
Yes
source
Synthesizes UTF-8 input, plain text or SSML, to a stream of bytes.
docs.aws.amazon.com/polly/latest/APIReference/API… · checked 2026-11-16
Credits kept when you change plannot stated on the pages we readnot stated on the pages we readnot stated on the pages we readYes
source
If you upgrade to a paid plan, any remaining Free Tier credit balance will automatically apply to your AWS bills.
aws.amazon.com/polly/pricing · checked 2026-11-16
Encryption in transit and at restnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readYes
source
including encryption at rest and in transit
aws.amazon.com/polly/faqs · checked 2026-11-16
ISO 27001not stated on the pages we readnot stated on the pages we readYes
source
for standards such as ISO 27001, ISO 27017, ISO 27018, SOC 2, SOC 3, and PCI DSS.
docs.cloud.google.com/document-ai/docs/security · checked 2026-11-16
not stated on the pages we read
PCI DSSnot stated on the pages we readnot stated on the pages we readYes
source
for standards such as ISO 27001, ISO 27017, ISO 27018, SOC 2, SOC 3, and PCI DSS.
docs.cloud.google.com/document-ai/docs/security · checked 2026-11-16
not stated on the pages we read
Usage dashboardYes
source
navigating to the analytics tab within the Developers dashboard
elevenlabs.io/pricing/api · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Automatic rechargenot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Mixed languages in one sentencenot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Voice localizationnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
IP indemnitynot stated on the pages we readnot stated on the pages we readYes
source
Google will defend Customer and its Affiliates using the Services under Customer’s Account and indemnify them
cloud.google.com/terms · checked 2026-11-16
not stated on the pages we read
CCPA compliantnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Voice quality (measured by us) 4 rows
FeatureElevenLabs CreatorOpenAI tts-1-hdGoogle Cloud Chirp 3: HD voicesAmazon Web Services Neural voices
Korean accuracy (character error rate, lower is better)not measured yetnot measured yetnot measured yetnot measured yet
English accuracy (word error rate, lower is better)not measured yetnot measured yetnot measured yetnot measured yet
Time to first soundnot measured yetnot measured yetnot measured yetnot measured yet
Human-preference quality (how pleasant it sounds)not measurednot measurednot measurednot measured
Billing (stated on the official pages) 45 rows

Show these 45 rows

Terms and ownership (stated on the official pages) 34 rows

Show these 34 rows

Data and privacy (stated on the official pages) 33 rows

Show these 33 rows

Limits (stated on the official pages) 23 rows

Show these 23 rows

Voices and models (stated on the official pages) 34 rows
FeatureElevenLabs CreatorOpenAI tts-1-hdGoogle Cloud Chirp 3: HD voicesAmazon Web Services Neural voices
Supported languagescount: 90; model: eleven_v4
source
90+ languages supported
elevenlabs.io/pricing/api · checked 2026-11-09
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)
source
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, …
developers.openai.com/api/docs/guides/text-to-spe… · checked 2026-11-09
count: 30 (Instant Custom Voice languages (counted from the table))
source
Instant Custom Voice is supported in the following languages:
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-09
41: Arabic (arb), Arabic (Gulf) (ar-AE), Catalan (ca-ES), Chinese (Cantonese) (yue-CN), Chinese (Mandarin) (cmn-CN), Czech (cs-CZ), Danish (da-DK), Dutch (Belgian) (nl-BE), Dutch (nl-NL), English (Australian) (en-AU), English (British) (en-GB), English (Indian) (en-IN), … +29 more (languages listed…
source
The following languages are supported by Amazon Polly and can be used to synthesize speech.
docs.aws.amazon.com/polly/latest/dg/supported-lan… · checked 2026-11-09
Bidirectional text streamingsupported: Yes (WebSocket generates audio from partial text input)
source
The Text-to-Speech WebSockets API is designed to generate audio from partial text input
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-09
not stated on the pages we readsupported: Yes (streaming synthesis; streaming is only compatible with Chirp 3: HD voices)
source
Streaming Cloud Text-to-Speech is only compatible with Chirp 3: HD voices .
cloud.google.com/text-to-speech/docs/create-audio… · checked 2026-11-09
supported: Yes; operation: StartSpeechSynthesisStream; transport: HTTP/2 bidirectional (text sent while audio flows back, without either side waiting for the other to finish)
source
Amazon Polly provides a StartSpeechSynthesisStream operation that establishes
docs.aws.amazon.com/polly/latest/dg/bidirectional… · checked 2026-11-09
Output formatsnot stated on the pages we readmp3, opus, aac, flac, wav, pcm
source
- **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. - **…
developers.openai.com/api/docs/guides/text-to-spe… · checked 2026-11-09
LINEAR16 (default), ALAW, MULAW, OGG_OPUS, PCM (Instant Custom Voice, streaming and batch)
source
streaming : LINEAR16 (default), ALAW , MULAW , OGG_OPUS , PCM
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-09
mp3, vorbis, pcm (audio stream formats named in the FAQ: MP3, Vorbis, raw PCM)
source
Amazon Polly supports MP3, Vorbis, and raw PCM audio stream formats.
aws.amazon.com/polly/faqs · checked 2026-11-09
Sdk languagespython, javascript
source
REST API and SDKs for Python, JavaScript, and more.
elevenlabs.io/pricing/api · checked 2026-11-09
javascript, python, go, java, csharp, ruby (official client libraries; Speech examples also show curl and the openai CLI)
source
Install an official client library from the [libraries page]
developers.openai.com/api/reference/overview.md · checked 2026-11-09
not stated on the pages we readJava 2.x, JavaScript v3, .NET v4, C++, Go v2, Kotlin, PHP v3, Ruby v3, Rust, Swift (AWS SDKs that support the bidirectional streaming API)
source
AWS SDK for Java 2.x, JavaScript v3, .NET v4, C++, Go v2, Kotlin,
docs.aws.amazon.com/polly/latest/dg/bidirectional… · checked 2026-11-09
Tts modelseleven_v4, eleven_v4_turbo, eleven_v3, eleven_v3_conversational, eleven_multilingual_v2, eleven_flash_v2_5, eleven_flash_v2
source
`eleven_v4_turbo`
elevenlabs.io/docs/overview/models.md · checked 2026-11-09
tts-1, tts-1-hd, gpt-4o-mini-tts
source
The `tts-1`, `tts-1-hd`, and `gpt-4o-mini-tts` models are deprecated and will
developers.openai.com/api/docs/guides/text-to-spe… · checked 2026-11-09
gemini-3.1-flash-tts-preview, gemini-2.5-flash-tts, gemini-2.5-pro-tts, gemini-2.5-flash-lite-preview-tts
source
Gemini-TTS includes the following available models:
cloud.google.com/text-to-speech/docs/gemini-tts · checked 2026-11-09
standard, neural, long-form, generative
source
Valid Values: standard | neural | long-form | generative
docs.aws.amazon.com/polly/latest/APIReference/API… · checked 2026-11-09
Clone sample secondsnot stated on the pages we readmax: 60 (audio samples for voices created from recordings)
source
The audio samples must be 60 seconds or less.
developers.openai.com/api/docs/guides/custom-voic… · checked 2026-11-09
max: 10 (Instant Custom Voice: up to 10 seconds of single-channel reference audio)
source
Record reference audio : Use your computer microphone to record up to 10
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-09
not stated on the pages we read
Custom voices maxnot stated on the pages we read20 (voices created from recordings, per organization)
source
At most 20 voices from recordings can be created per organization.
developers.openai.com/api/docs/guides/custom-voic… · checked 2026-11-09
unlimited (no limit on the number of voice cloning keys (Instant Custom Voice))
source
There is no limit to the number of voice cloning keys that you can create,
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-09
not stated on the pages we read
Emotion controlnot stated on the pages we readYes (gpt-4o-mini-tts, through prompts: accent, emotional range, intonation, impressions, speed of speech, tone, whispering)
source
`gpt-4o-mini-tts` lets you use prompts to control these aspects of speech:
developers.openai.com/api/docs/guides/text-to-spe… · checked 2026-11-09
Yes (Gemini-TTS style control: natural-language prompts steer accent, tone and expressions incl. whisper, pace)
source
Style control : Using natural language prompts, you can adapt the
cloud.google.com/text-to-speech/docs/gemini-tts · checked 2026-11-09
not stated on the pages we read
Voice cloning apiinstant and professional voice clones can be created through the API
source
Create IVC voice
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-09
Yes
source
Voices from recordings must be created through an API request.
developers.openai.com/api/docs/guides/custom-voic… · checked 2026-11-09
not stated on the pages we readnot stated on the pages we read
Voice designYes
source
Design a voice
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-09
Yes (prompt-to-voice is generally available to all API customers; prompt-generated voices work with GPT-Live only)
source
Prompt-to-voice is generally available to all API customers.
developers.openai.com/api/docs/guides/custom-voic… · checked 2026-11-09
Yes (Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS: voice design and voice replication in Preview, through the Agent Platform API and Agent Studio (not through the Cloud Text-to-Speech API))
source
Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS are Generally Available (GA) through the Agent Platform API and Agent Studio (with voice design and voice replication in Preview). They aren't available through the Cloud Text-to-Speech API.
cloud.google.com/text-to-speech/docs/gemini-tts · checked 2026-11-16
not stated on the pages we read
Clone sample formatsnot stated on the pages we readmpeg, wav, ogg, aac, flac, webm, mp4
source
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-voic… · checked 2026-11-09
LINEAR16, PCM, MP3, M4A (Instant Custom Voice supported encoding formats)
source
LINEAR16 , PCM , MP3 , M4A
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-09
not stated on the pages we read
Cross lingual synthesisMultilingual v2 keeps voice quality and personality across all supported languages, maintaining the speaker's characteristics and accent
source
The model delivers consistent voice quality and personality across all supported languages while maintaining the speaker's unique characteristics and accent.
elevenlabs.io/docs/overview/models.md · checked 2026-11-09
not stated on the pages we readen-US voice cloning keys can synthesize de-DE, es-US, es-ES, fr-CA, fr-FR, pt-BR (Instant Custom Voice language transfer)
source
Language transfers : Voice cloning keys with locale en-US can synthesize output in the following locales: de-DE , es-US , es-ES , fr-CA , fr-FR , pt-BR
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-09
some alphabets are not read by all voices (e.g. Cyrillic by English voices) unless phoneme mapping is used
source
Some alphabets might not be available with all the voices (for example, Cyrillic might not be read at all by English voices) unless phoneme mapping is used.
docs.aws.amazon.com/polly/latest/APIReference/API… · checked 2026-11-09
Builtin voicesnot stated on the pages we read9: alloy, ash, coral, echo, fable, onyx, nova, sage, shimmer
source
The `tts-1` and `tts-1-hd` models support a smaller set: `alloy`, `ash`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, and `shimmer`.
developers.openai.com/api/docs/guides/text-to-spe… · checked 2026-11-09
count: 30 (Chirp 3: HD voices in 30 distinct styles across many languages)
source
These voices are in 30 distinct styles across many languages
cloud.google.com/text-to-speech/docs/list-voices-… · checked 2026-11-09
106: Aditi, Amy, Astrid, Bianca, Brian, Camila, Carla, Carmen, Celine, Chantal, Conchita, Cristiano, … +94 more (VoiceId valid values of SynthesizeSpeech (Aditi ... Tiffany))
source
Valid Values: Aditi | Amy | Astrid
docs.aws.amazon.com/polly/latest/APIReference/API… · checked 2026-11-09
Cloned voice supported apisTTS API: any library voice by ID, including professional, cloned and designed voices
source
You can reference any voice in your library by ID, including professional voices, cloned voices, and voices you've designed.
elevenlabs.io/pricing/api · checked 2026-11-09
GPT-Live, Text to Speech API, Realtime API, Chat Completions API with audio output
source
These voices can be used with GPT-Live, the [Text to Speech API]
developers.openai.com/api/docs/guides/custom-voic… · checked 2026-11-09
not stated on the pages we readnot stated on the pages we read
First response latency msms: 100; stat: median latency (excl. application & network); model: eleven_v4_turbo
source
Ultra-low latency (median latency of ~100ms†)
elevenlabs.io/docs/overview/models.md · checked 2026-11-16
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Language override paramYes
source
Language code (ISO 639-1) used to enforce a language for the model and text normalization.
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-09
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Model api availabilityEleven v4: via the Text to Dialogue API
source
Eleven v4 is available via the [Text to Dialogue API]
elevenlabs.io/docs/overview/models.md · checked 2026-11-09
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
source
`gpt-realtime-2.1-mini` isn't a supported model for `/v1/audio/speech`.
developers.openai.com/api/docs/guides/text-to-spe… · checked 2026-11-09
Gemini 3.8 Flash TTS and Flash-Lite TTS (incl. voice design and voice replication): Preview through the Gemini Enterprise API only; not available through the Cloud Text-to-Speech API
source
They aren't available through the Cloud Text-to-Speech API.
cloud.google.com/text-to-speech/docs/gemini-tts · checked 2026-11-09
not stated on the pages we read
Model generation statusEleven v3 (and v3 Conversational): previous generation
source
Eleven v3 is our previous generation speech synthesis model
elevenlabs.io/docs/overview/models.md · checked 2026-11-09
not stated on the pages we readlatest TTS models (LLM-powered)
source
Latest TTS models
cloud.google.com/text-to-speech/pricing · checked 2026-11-09
not stated on the pages we read
Recommended replacementeleven_flash_v2_5 (for eleven_turbo_v2_5)
source
First generation low-latency model (outclassed by Flash models)
elevenlabs.io/docs/overview/models.md · checked 2026-11-09
gpt-realtime-2.1-mini (Realtime API)
source
| **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 · checked 2026-11-16
not stated on the pages we readnot stated on the pages we read
Streaming synthesis start triggernot stated on the pages we readnot stated on the pages we readonly after the client sends half-close (no more input) (Gemini-TTS streaming on Cloud Text-to-Speech API)
source
synthesizing when the client sends Half-Close as a signal that it won't send
cloud.google.com/text-to-speech/docs/gemini-tts · checked 2026-11-09
as input text arrives: text is sent as it becomes available (e.g. a model generating token by token) and audio is returned as it is synthesized
source
You send text as it becomes available, and Amazon Polly returns audio as it synthesizes,
docs.aws.amazon.com/polly/latest/dg/bidirectional… · checked 2026-11-09
Target use caseEleven v4: character voiceovers, emotional dialogue, audiobook production, multilingual projects; content creation (professional content, audiobooks, video narration)
source
Perfect for long-form narration with complex emotional delivery.
elevenlabs.io/docs/overview/models.md · checked 2026-11-09
high quality text-to-speech
source
The tts-1-hd model is optimized for high quality text-to-speech use cases.
developers.openai.com/api/docs/models/tts-1-hd.md · checked 2026-11-09
intended for Conversational Agents; examples: chat experiences, virtual assistants, customer service chatbots, interactive education, sales and pitches, storytime
source
Conversational Agents
cloud.google.com/text-to-speech/docs/list-voices-… · checked 2026-11-09
not stated on the pages we read
Optimized foreleven_flash_v2_5 / eleven_flash_v2: real-time use (~75 ms)
source
Ultra-fast model optimized for real-time use
elevenlabs.io/docs/overview/models.md · checked 2026-11-09
quality
source
Text-to-speech model optimized for quality
developers.openai.com/api/docs/models/tts-1-hd.md · checked 2026-11-09
Gemini 3.1 Flash TTS and Gemini 2.5 Flash TTS: low latency, controllable, single- and multi-speaker audio for cost-efficient everyday applications
source
Low latency, controllable, single- and multi-speaker Cloud TTS audio generation for cost-efficient everyday applications
cloud.google.com/text-to-speech/docs/gemini-tts · checked 2026-11-09
not stated on the pages we read
Relative latency qualityMultilingual v2: higher latency and cost per character than Flash models, superior quality
source
While it has a higher latency & cost per character than Flash models, it delivers superior quality for projects where lifelike speech is important.
elevenlabs.io/docs/overview/models.md · checked 2026-11-09
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Ssml parsingYes
source
enable_ssml_parsing boolean Optional Defaults to false
elevenlabs.io/docs/api-reference/text-to-speech/v… · checked 2026-11-09
not stated on the pages we readNo (Chirp 3: HD voices do not support SSML input, speaking rate and pitch audio parameters, or the A-Law audio encoding)
source
Chirp 3: HD voices doesn't support SSML input, speaking rate and pitch-audio parameters, and the A-Law audio encoding.
cloud.google.com/text-to-speech/docs/list-voices-… · checked 2026-11-09
Yes (input is UTF-8 plain text or SSML; SSML input must be valid, well-formed SSML)
source
Synthesizes UTF-8 input, plain text or SSML, to a stream of bytes.
docs.aws.amazon.com/polly/latest/APIReference/API… · checked 2026-11-09
Streaming model supportnot stated on the pages we readnot stated on the pages we readnot stated on the pages we readgenerative engine only (StartSpeechSynthesisStream (bidirectional streaming) requires the generative engine and an AWS SDK that supports HTTP/2 event streams)
source
This operation requires the generative engine and an AWS SDK that supports HTTP/2
docs.aws.amazon.com/polly/latest/dg/bidirectional… · checked 2026-11-09
Voice cloning eligibilitynot stated on the pages we readeligible customers only; contact sales; once enabled for the organization the Voices tab under Audio is available
source
Custom voices created from recordings are limited to eligible customers.
developers.openai.com/api/docs/guides/custom-voic… · checked 2026-11-09
voice cloning (Instant Custom Voice) restricted to allow-listed users; request access from the sales team
source
Important: Access to Instant Custom Voice is restricted to allow-listed users.
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-09
not stated on the pages we read
Custom voice accentsnot stated on the pages we readEnglish accents (gpt-live-1 custom voices; accent set in session.instructions)
source
`gpt-live-1` supports custom voices with English accents.
developers.openai.com/api/docs/guides/custom-voic… · checked 2026-11-09
not stated on the pages we readnot stated on the pages we read
Web playgroundnot stated on the pages we readOpenAI.fm interactive demo for trying the voices and the latest text-to-speech model
source
Hear and play with these voices in [OpenAI.fm](https://openai.fm), our interactive demo
developers.openai.com/api/docs/guides/text-to-spe… · checked 2026-11-09
not stated on the pages we readnot stated on the pages we read
Api backward compatibility policynot stated on the pages we readnot stated on the pages we readat least 12 months’ notice before significantly modifying a Customer-facing Google API in a backwards-incompatible manner (not for pre-GA offerings)
source
Customer-facing Google API in a backwards-incompatible manner.
cloud.google.com/terms · checked 2026-11-09
not stated on the pages we read
Child voices allowedno: voice recordings of anyone under 18 may not be used to create or train a voice model
source
You may not submit voice recordings of anyone under 18 to create or train a voice model.
elevenlabs.io/use-policy · checked 2026-11-09
not stated on the pages we readnot stated on the pages we readnot stated on the pages we read
Dated model snapshotsnot stated on the pages we readYes (gpt-4o-mini-tts: default snapshot gpt-4o-mini-tts-2025-12-15; also gpt-4o-mini-tts-2025-03-20)
source
Default snapshot: `gpt-4o-mini-tts-2025-12-15`
developers.openai.com/api/docs/models/gpt-4o-mini… · checked 2026-11-09
not stated on the pages we readnot stated on the pages we read
Language quality tiernot stated on the pages we readvoices are currently optimized for English
source
Voices are currently optimized for English.
developers.openai.com/api/docs/guides/text-to-spe… · checked 2026-11-09
not stated on the pages we readnot stated on the pages we read
Voice cloning rpmnot stated on the pages we readnot stated on the pages we read10 (voice cloning key creation per minute per project (GenerateVoiceCloningKeyRequestsPerMinutePerProject))
source
You can create 10 voice cloning keys per minute per project.
cloud.google.com/text-to-speech/docs/chirp3-insta… · checked 2026-11-09
not stated on the pages we read
Voice design candidatesnot stated on the pages we read1
source
It doesn't include audio or a preview
developers.openai.com/api/docs/guides/custom-voic… · checked 2026-11-09
not stated on the pages we readnot stated on the pages we read
Support and service (stated on the official pages) 4 rows

Show these 4 rows

Other features (stated on the official pages) 31 rows

Show these 31 rows

A transcript error can come from the transcriber and not from the voice. The same transcriber is used for every plan, so the order between plans is comparable and the absolute value is not. How pleasant a voice sounds is not measured.

Accuracy is measured by transcribing each plan's audio with one local speech-to-text model and comparing the text with the sentence; a number written another way (digits for words) counts as an error. How pleasant a voice sounds is not measured.