Managed speech service with character-credit billing, streaming/file audio and optional timing data. Available engines and voices depend on the customer contract.
streaming=1 defaults to a redirect to the streaming server; 0 waits for complete generation. Header-dependent formats such as WAV/A-law/mu-law are fully generated before transfer.
Batch processing
Not collected
No reviewed model-specific specification; unknown does not mean unsupported.
Fine-tuning
Not collected
No reviewed model-specific specification; unknown does not mean unsupported.
Reasoning
Not collected
No reviewed model-specific specification; unknown does not mean unsupported.
Context caching
Not collected
No reviewed model-specific specification; unknown does not mean unsupported.
Base model
Not collected
No reviewed model-specific specification; unknown does not mean unsupported.
Default excludes whitespace; order confirmation may specify another limit. Not a token window.
Request quotas
Intended usage up to 25,000 requests/day and 2,000 requests in a single hour. Capacity, real-time channels and generation speed are contracted; this is not a universal requests-per-second guarantee.Source for Request quotas (opens in a new tab)
The PDF separately labels U-law/A-law WAV as 16 bit/8 kHz; codec wording is retained as a documentation ambiguity, not generalized to every format.
Response format
Timing-only call returns JSON and consumes the same credits as an audio call. RSDS combines audio and timing in one response with no extra timing credits; parse the container. RSDS audio is MP3 at 48 kbit/s only and is not available for every voice.Source for Response format (opens in a new tab)
Authentication
Customer-specific API key in every request. Portal supplies integration instructions and key rotation. Public marketing endpoint examples are explicitly illustrative.Source for Authentication (opens in a new tab)
Voice controls
Language, voice, volume, pitch, speaking rate, audio parameters and customer dictionary. SSML supports prosody, pauses, phonetic transcriptions and switching voice/language. Dictionaries are voice-specific.Source for Voice controls (opens in a new tab)
Complete entitled voice list comes from account/API. Website samples are cross-product examples, not a verified SCAPI API inventory.
Language coverage
Product page advertises 90 languages/300 voices; June 2026 specification says 50+/200+. Exact language/voice access is determined by the order and account inventory.Source for Language coverage (opens in a new tab)
Count discrepancy is retained; do not infer a complete current locale matrix from either total.
Published price
Standard meter: one credit per non-whitespace character, including pronunciation-dictionary changes. Currency tariff is quoted. Alternative per-second terms may apply. Capacity period defaults to one year only when the order omits it.Source for Published price (opens in a new tab)
Model terms
Generated audio may not be stored, reused or redistributed unless expressly allowed by the order confirmation. Exceeding licensed capacity returns an error. When generation-speed limits apply, a channel can remain occupied for the full audio playback duration.Source for Model terms (opens in a new tab)
Creation privacy
Provider Privacy Notice v1.4 (April 3, 2026) states voice-model improvement uses actor-recorded data, not customer input. It also discloses third-party engines depending on selected voice. Its controller notice excludes embedded-service processing where ReadSpeaker acts as processor; the integrating organization and applicable DPA govern that use. Exact inference retention, opt-out controls and processing location remain unverified. EU corporate address is not a residency guarantee.Source for Creation privacy (opens in a new tab)
Documentation discrepancy
SCAPI 4.19 is a service version, not a neural model release. Marketing examples defer exact URL and parameters to customer documentation. Product language totals differ from the June 2026 specification, and the PDF has ambiguous A-law/mu-law bit-depth wording.Source for Documentation discrepancy (opens in a new tab)
Access & pricing
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
Customer voice selector and exact API route are supplied through onboarding; no checkpoint ID established.
Access
HTTPS REST with customer key, text, voice and audio configuration; streamed, complete-file or RSDS audio. Exact endpoint and parameter contract supplied through the customer portal.
Regions
Hosted by ReadSpeaker; exact processing location unverified.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 16 Oct 2026
Category
Usage
Rate
Unit
Contract character credits
Speech generation1
1 credit
non-whitespace character
Rate conditions
Includes changes introduced by pronunciation dictionaries. Numeric currency price and alternative per-second contracts require a quote. RSDS includes timing with audio for the single audio-call charge; a separate timing request is charged again. Not a text-token or per-question tariff.
Order controls capacity, period, voice entitlement and audio-storage/reuse rights. Provider Privacy Notice v1.4 (April 3, 2026) states voice-model improvement uses actor-recorded data, not customer input. It also discloses third-party engines depending on selected voice. Its controller notice excludes embedded-service processing where ReadSpeaker acts as processor; the integrating organization and applicable DPA govern that use. Exact inference retention, opt-out controls and processing location remain unverified. EU corporate address is not a residency guarantee.
Customer voice selector and exact API route are supplied through onboarding; no checkpoint ID established.
Access
Separate HTTPS timing-information call returns JSON, billed at the audio-call character rate. Exact route supplied through customer documentation.
Regions
Hosted by ReadSpeaker; exact processing location unverified.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 16 Oct 2026
Category
Usage
Rate
Unit
Contract character credits
Separate timing request1
1 credit
non-whitespace character
Rate conditions
Includes changes introduced by pronunciation dictionaries. Numeric currency price and alternative per-second contracts require a quote. RSDS includes timing with audio for the single audio-call charge; a separate timing request is charged again. Not a text-token or per-question tariff.
Order controls capacity, period, voice entitlement and audio-storage/reuse rights. Provider Privacy Notice v1.4 (April 3, 2026) states voice-model improvement uses actor-recorded data, not customer input. It also discloses third-party engines depending on selected voice. Its controller notice excludes embedded-service processing where ReadSpeaker acts as processor; the integrating organization and applicable DPA govern that use. Exact inference retention, opt-out controls and processing location remain unverified. EU corporate address is not a residency guarantee.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
ReadSpeaker speechCloud API
Not verified
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
How it works
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
Minimum reusable input
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
Lifetime & refresh
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
How to enable it
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
Usage fields
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
Billing rules
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
Limits & data boundaries
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 Oct 2026
ReadSpeaker speechCloud API
Not verified
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
How it works
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
Minimum reusable input
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
Lifetime & refresh
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
How to enable it
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
Usage fields
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
Billing rules
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
Limits & data boundaries
Not collected
No reviewed inference-cache contract. Downloaded voice files, dictionaries, generated-audio reuse and runtime memory are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 Oct 2026
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Licensed proprietary hosted service with customer-selected voices. Provider privacy documentation discloses native and third-party engines; the service is not asserted to be a separate native base model.
