Text-to-speech API
Google Cloud Text-to-Speech
Text to speech over a REST and gRPC API, billed per character with a rate and a monthly free amount for each voice type.
Plans
Values that apply to one plan. "Not stated" means the official pages do not say; it is not an estimate.
| Plan | Price | Included | Extra usage | Concurrency | Rate limit | Buy |
|---|---|---|---|---|---|---|
| Chirp 3: HD voicesPay as you go | Not recorded |
Not recorded |
Pricing pageChoose the plan on the page | |||
| WaveNet voicesPay as you go | Not recorded |
Not recorded |
Pricing pageChoose the plan on the page | |||
| Standard voicesPay as you go | Not recorded |
Not recorded |
Pricing pageChoose the plan on the page | |||
| Neural2 voicesPay as you go | Not recorded |
Not recorded |
Pricing pageChoose the plan on the page | |||
| Studio voicesPay as you go | Not recorded |
Not recorded |
Pricing pageChoose the plan on the page | |||
| Polyglot (Preview) voicesPay as you go | Not recorded |
Not recorded |
Pricing pageChoose the plan on the page |
Applies to every plan
Recorded for the product or the provider; a plan-level value or a listed exception replaces it.
Collection notes
Six voice types of the Cloud Text-to-Speech API are the plans here, each billed by use per character with its own monthly free amount: Chirp 3 HD, WaveNet, Standard, Neural2, Studio and Polyglot (Preview). Not modelled: Instant Custom Voice (allow-listed, $60 per million characters, no free amount) and the Gemini-TTS models (priced per token, with no characters-per-token conversion on the page). The pages checked do not say whether customer text is used to train models, and no Text-to-Speech entry is on the supported-products page of the Google Cloud remote MCP servers. Authentication is by Application Default Credentials; the page does not mention API keys.
Sources and notes
Each number points to the provider's own sentence, as it appears on the page on the date shown.
Streaming Cloud Text-to-Speech is only compatible with Chirp 3: HD voices
The API accepts a stream of requests with type StreamingSynthesizeRequest , which contain either StreamingSynthesisInput or StreamingSynthesizeConfig .
The streaming method is in Preview.
Korean (South Korea) Premium ko-KR ko-KR-Chirp3-HD-Achernar FEMALE
Chirp 3: HD voices (sku:F977-2280-6F1B) 0 to 1 million characters US$0.00003 per character
How the value follows from the source: The price per character times 1,000: $0.03 per 1,000 characters ($30 per 1 million).
will be automatically charged if your usage exceeds the number of free characters allowed per month
How the value follows from the source: 1,000,000 free characters a month at $30 per 1 million characters.
How the value follows from the source: $30 per 1 million characters.
The page says streaming synthesis works with Chirp 3: HD voices only.
Korean (South Korea) Premium ko-KR ko-KR-Wavenet-A FEMALE
WaveNet voices (sku:9D01-5995-B545) 0 to 4 million characters US$0.000004 per character
How the value follows from the source: The price per character times 1,000: $0.004 per 1,000 characters ($4 per 1 million).
How the value follows from the source: 4,000,000 free characters a month at $4 per 1 million characters.
How the value follows from the source: $4 per 1 million characters.
Korean (South Korea) Standard ko-KR ko-KR-Standard-A FEMALE
Standard voices (sku:9D01-5995-B545) 0 to 4 million characters US$0.000004 per character
Korean (South Korea) Premium ko-KR ko-KR-Neural2-A FEMALE
Neural2 voices (sku:FEBD-04B6-769B) 0 to 1 million characters US$0.000016 per character
How the value follows from the source: The price per character times 1,000: $0.016 per 1,000 characters ($16 per 1 million).
How the value follows from the source: 1,000,000 free characters a month at $16 per 1 million characters.
How the value follows from the source: $16 per 1 million characters.
The voice list read shows no Korean voice of this type.
Studio voices (sku:84AB-48C0-F9C3) 0 to 1 million characters US$0.00016 per character
How the value follows from the source: The price per character times 1,000: $0.16 per 1,000 characters ($160 per 1 million).
How the value follows from the source: 1,000,000 free characters a month at $160 per 1 million characters.
How the value follows from the source: $160 per 1 million characters.
Polyglot (Preview) voices (sku:FEBD-04B6-769B) 0 to 1 million characters US$0.000016 per character