/ Deepgram / Flux TTS Deepgram / Flux TTS
Flux TTS Streaming text-to-speech with turn-aware delivery, interruption reporting and consistent prosody across turns.
available Closed weights Text-to-speech Speech generation
Context window Not collected Awaiting source review
Maximum output Not collected Awaiting source review
Input billing See rates Deepgram API · REST
Output billing See rates Published units and conditions below
Specifications Access & pricing Caching Voices Evaluation Sources & lifecycle
Specifications Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
Context / input limit Not collected
Maximum output Not collected
Reasoning Not collected
Tool calling Not collected
Structured output Not collected
Batch processing Not collected
Fine-tuning Not collected
Knowledge cutoff Not collected
Release date Not collected
Parameters Not collected
Architecture Not collected Context caching Not collected See endpoint caching records. No verified support claim for this model.
Access & pricing Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
API model ID flux-haley-en
Access REST synthesis using /v2/speak. A complete voice model string is required; choose from the voice catalog.
Regions Regional routing and residency terms have not been verified for this endpoint. Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 12 Oct 2026 Category Usage Rate Unit Pay As You Go Speech synthesis1 $0.045 1,000 characters Growth Speech synthesis2 $0.0405 1,000 characters
Rate conditions Standard PAYG character rate. Billing credits or promotional credits are not treated as rate discounts. Alternative prepaid Growth plan rate, requiring $4,000+/year. Not an additional charge on top of PAYG. Pricing source (opens in a new tab) Data & enterprise terms Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
API model ID flux-haley-en
Access WebSocket streaming using /v2/speak. A complete voice model string is required; choose from the voice catalog.
Regions Regional routing and residency terms have not been verified for this endpoint. Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 12 Oct 2026 Category Usage Rate Unit Pay As You Go Speech synthesis1 $0.045 1,000 characters Growth Speech synthesis2 $0.0405 1,000 characters
Rate conditions Standard PAYG character rate. Billing credits or promotional credits are not treated as rate discounts. Alternative prepaid Growth plan rate, requiring $4,000+/year. Not an additional charge on top of PAYG. Pricing source (opens in a new tab) Data & enterprise terms Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Caching Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUT Process & retain The system processes eligible input and retains reusable state.
02 / LATER REQUEST Check available state Reuse depends on matching input, session state and the cache policy.
03 / CACHE HIT Reuse & generate Reusing state can reduce repeated work. Any charges follow the billing rules below.
Deepgram API · REST flux-haley-enNot verified Provider-side caching has not been verified for this endpoint. Missing documentation is not evidence that caching is unsupported.
How it works Not collected
Minimum reusable input Not collected
Lifetime & refresh Not collected
How to enable it Not collected
Usage fields Not collected
Billing rules Not collected
Limits & data boundaries Not collected No verified cache rate for this endpoint. An empty rate is not a zero charge.
Deepgram API · WebSocket flux-haley-enNot verified Provider-side caching has not been verified for this endpoint. Missing documentation is not evidence that caching is unsupported.
How it works Not collected
Minimum reusable input Not collected
Lifetime & refresh Not collected
How to enable it Not collected
Usage fields Not collected
Billing rules Not collected
Limits & data boundaries Not collected No verified cache rate for this endpoint. An empty rate is not a zero charge.
Voice choices 36 voices Choose a voice within Flux TTS. These are API voice identifiers, not additional model releases. Source links document each voice.
Find a voice Published voice catalog Voice / API ID Language & accent Delivery Hannahflux-hannah-en en Clear, confident, thoughtful, pleasant, niceVoice source (opens in a new tab) Kitflux-kit-en en Friendly, energetic, thoughtful, calm, helpfulVoice source (opens in a new tab) Alexisflux-alexis-en en Clear, professional, calm, caring, empatheticVoice source (opens in a new tab) Cliffflux-cliff-en en Deep, confident, calm, raspy, clearVoice source (opens in a new tab) Siennaflux-sienna-en en Clear, professional, calm, warm, caringVoice source (opens in a new tab) Coleflux-cole-en en Friendly, clear, interesting, energetic, engagingVoice source (opens in a new tab) Brookeflux-brooke-en en Friendly, intelligent, fast, confident, energeticVoice source (opens in a new tab) Colinflux-colin-en en Warm, friendly, trustworthy, confident, authoritativeVoice source (opens in a new tab)
Show all 36 voices
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 Deepgram describes its speech model weights as proprietary, including private deployment under provider control. These named native speech models are catalogued separately from its hosted open-weight Whisper service.
Classification evidence (opens in a new tab) Sources reviewed