No reviewed model-specific contract; unknown does not mean unsupported.
Fine-tuning
Not collected
No reviewed model-specific contract; unknown does not mean unsupported.
Reasoning
Not collected
No reviewed model-specific contract; unknown does not mean unsupported.
Context caching
Not collected
No reviewed model-specific contract; unknown does not mean unsupported.
Base model
Not collected
No reviewed model-specific contract; unknown does not mean unsupported.
Published price
No reviewed public inference tariff. The account-balance API reports NGN for Nigerian accounts and USD for other countries, but a balance or sample balance is not a per-minute, character, token or question price.Source for Published price (opens in a new tab)
Select voice_language, voice_accent and voice_gender (male/female). No stable per-speaker voice_id catalog is published in the reviewed contract.Source for Voice controls (opens in a new tab)
Output accents
English accents: afrikaans, hausa, igbo, luganda, sepedi, swahili, setswana, xhosa, yoruba and zulu. Other languages list their corresponding accent.Source for Output accents (opens in a new tab)
Generate/enqueue prose: 4096 characters. Error examples instead mention 100 and 1200 respectively. Confirm the enforced file limit; streaming accepts 10–100 characters per chunk.Source for Maximum prompt characters (opens in a new tab)
Conflicting examples are preserved rather than choosing a false universal numeric cap.
Request limits
Generate: 30 requests/minute; enqueue: 60/minute. Streaming: 300-second session, 60-second idle gap, 3 connections/minute and 3 concurrent connections.Source for Request limits (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.
The reviewed API exposes language or workflow controls, not an immutable model selector.
Access
POST https://infer.voice.intron.io/tts/v1/generate; Bearer API key; JSON text, voice_language, voice_accent, voice_gender; optional output_audio_format. Returns an audio path; processing may time out after 120 seconds with a text ID for polling.
Regions
Hosted processing region not established. Offline local deployment is a separately described commercial option, not proof of the hosted API location.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
The linked June 2024 privacy policy includes related websites, apps and APIs, including speech data. It permits service operation and improvement, and sharing for support, analytics, internal research and other stated business purposes. Retention depends on purpose and legal requirements; no universal TTL or zero-retention promise is established. Transcribe App terms preserve customer-data ownership and license processing for service operation, legal duties and written permission. A specific model-training opt-out, complete subprocessor regions and newer customer-specific terms remain unresolved.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
The linked June 2024 privacy policy includes related websites, apps and APIs, including speech data. It permits service operation and improvement, and sharing for support, analytics, internal research and other stated business purposes. Retention depends on purpose and legal requirements; no universal TTL or zero-retention promise is established. Transcribe App terms preserve customer-data ownership and license processing for service operation, legal duties and written permission. A specific model-training opt-out, complete subprocessor regions and newer customer-specific terms remain unresolved.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
The linked June 2024 privacy policy includes related websites, apps and APIs, including speech data. It permits service operation and improvement, and sharing for support, analytics, internal research and other stated business purposes. Retention depends on purpose and legal requirements; no universal TTL or zero-retention promise is established. Transcribe App terms preserve customer-data ownership and license processing for service operation, legal duties and written permission. A specific model-training opt-out, complete subprocessor regions and newer customer-specific terms remain unresolved.
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.
Intron Voice API / enterprise
Not verified
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
How it works
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Minimum reusable input
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Lifetime & refresh
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
How to enable it
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Usage fields
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Billing rules
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Limits & data boundaries
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 Oct 2026
Intron Voice API / enterprise
Not verified
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
How it works
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Minimum reusable input
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Lifetime & refresh
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
How to enable it
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Usage fields
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Billing rules
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Limits & data boundaries
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 Oct 2026
Intron Voice API / enterprise
Not verified
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
How it works
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Minimum reusable input
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Lifetime & refresh
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
How to enable it
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Usage fields
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Billing rules
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances are not prompt caching.
Limits & data boundaries
Not collected
No model-specific inference-cache contract verified. Stored files, streaming buffers and account balances 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
Kinyarwanda MOS
Intron · provider-reported
4.67MOS
Provider table reports n=100; the sampling unit is not specified as raters, ratings or clips. Chart scale extends to 5. No confidence interval or independent reproduction established. Preserve language-specific evaluations; do not treat absent competitor cells as zero or infer a universal voice-quality ranking.
Provider table reports n=249; the sampling unit is not specified as raters, ratings or clips. Chart scale extends to 5. No confidence interval or independent reproduction established. Preserve language-specific evaluations; do not treat absent competitor cells as zero or infer a universal voice-quality ranking.
Provider table reports n=378; the sampling unit is not specified as raters, ratings or clips. Chart scale extends to 5. No confidence interval or independent reproduction established. Preserve language-specific evaluations; do not treat absent competitor cells as zero or infer a universal voice-quality ranking.
Provider table reports n=369; the sampling unit is not specified as raters, ratings or clips. Chart scale extends to 5. No confidence interval or independent reproduction established. Preserve language-specific evaluations; do not treat absent competitor cells as zero or infer a universal voice-quality ranking.
Provider table reports n=197; the sampling unit is not specified as raters, ratings or clips. Chart scale extends to 5. No confidence interval or independent reproduction established. Preserve language-specific evaluations; do not treat absent competitor cells as zero or infer a universal voice-quality ranking.
Provider table reports n=387; the sampling unit is not specified as raters, ratings or clips. Chart scale extends to 5. No confidence interval or independent reproduction established. Preserve language-specific evaluations; do not treat absent competitor cells as zero or infer a universal voice-quality ranking.
Provider table reports n=179; the sampling unit is not specified as raters, ratings or clips. Chart scale extends to 5. No confidence interval or independent reproduction established. Preserve language-specific evaluations; do not treat absent competitor cells as zero or infer a universal voice-quality ranking.
Provider table reports n=16; the sampling unit is not specified as raters, ratings or clips. Chart scale extends to 5. No confidence interval or independent reproduction established. Preserve language-specific evaluations; do not treat absent competitor cells as zero or infer a universal voice-quality ranking.
Provider table reports n=282; the sampling unit is not specified as raters, ratings or clips. Chart scale extends to 5. No confidence interval or independent reproduction established. Preserve language-specific evaluations; do not treat absent competitor cells as zero or infer a universal voice-quality ranking.
Provider table reports n=559; the sampling unit is not specified as raters, ratings or clips. Chart scale extends to 5. No confidence interval or independent reproduction established. Preserve language-specific evaluations; do not treat absent competitor cells as zero or infer a universal voice-quality ranking.
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
Commercial Sahara model family described by its provider alongside proprietary training and reserved service technology. No exact Sahara checkpoint was found among the reviewed public research weights. Family names and benchmark versions do not establish immutable API selectors.
