canonical: https://jentic.com/apis/fliki.ai/fliki

# Fliki API

The Fliki API is the Enterprise interface to Fliki's AI text-to-speech and text-to-video platform. It exposes voice, language, and dialect catalogs, and two generation endpoints that turn text into either an audio file or a fully assembled video. The API is intentionally narrow: it covers the discovery of available voices and languages, then the creation of media from a text prompt.

## For AI agents

Generate AI voiceovers and text-to-video clips from a script, choosing from Fliki's voice and language catalog.

## Scope

Does not handle video editing timelines, live streaming, or transcription - use for AI text-to-speech and text-to-video generation only.

## Capabilities

- Generate an AI voiceover from a script using a chosen voice and language
- Generate a fully assembled video from a script with synchronized voiceover
- List supported languages for text-to-speech and text-to-video generation
- List dialects available within a language to fine-tune accent and locale
- Browse the catalog of AI voices including gender, style, and language coverage
- Pick a voice that matches a target audience before generating media

## Use cases

### Automated marketing video creation

Marketing teams turn written ad copy and product descriptions into short-form videos by posting the script to `/generate/video` with a chosen voice. Fliki returns a finished MP4 with synchronized voiceover, removing the manual edit step. The same flow scales to localized versions by re-running with a different language or dialect.

Example prompt: Generate a video from a 90-word product script using a US English female voice and return the resulting video URL

### Audio version of written content

Publishers and bloggers create audio versions of articles by sending the article text to `/generate/audio` with a chosen voice. The endpoint returns an MP3 file that can be hosted as a podcast episode or embedded in the original article, expanding accessibility without hiring voice talent.

Example prompt: Generate an audio version of a 1,200-word article using a calm narrative voice and return the MP3 download URL

### Localized content in multiple languages

Customer-education and onboarding teams produce localized voiceovers by querying /languages and /dialects for supported locales, then calling `/generate/audio` or `/generate/video` for each one. The voice catalog returned by /voices lets the agent choose a regionally appropriate voice for each output.

Example prompt: Pick the most popular female voice for each of fr-FR, es-ES, and de-DE, then generate the same script in all three locales

### AI agent narrated explainer

An AI agent that produces written explainers can pipe its output directly into Fliki to deliver narrated audio or video. Through Jentic, the agent searches by intent and gets the right Fliki endpoint and voice catalog without hard-coding API paths, so the same skill works whether the user wants an MP3 or a finished video.

Example prompt: Given a 200-word explainer the agent has just written, generate an MP4 with a male documentary voice in en-US

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/languages` | List supported languages |
| GET | `/dialects` | List supported dialects |
| GET | `/voices` | List available AI voices |
| POST | `/generate/audio` | Generate an audio voiceover from text |
| POST | `/generate/video` | Generate a video with voiceover from text |

## Key resources

- **Voices** — Browse the catalog of AI voices and their language coverage
- **Languages** — List supported languages for audio and video generation
- **Dialects** — List supported dialects within each language for accent control
- **Audio Generation** — Generate an MP3 voiceover from a text script
- **Video Generation** — Generate an MP4 video with synchronized voiceover from a script

## Why Jentic

- **Setup:** Wiring the Fliki API by hand means setting its bearer auth, looking up language, dialect, and voice IDs before each generation, and handling retries yourself. Through Jentic you install once, import Fliki from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** Fliki carries its generation target in the request body rather than as an owned resource in the URL path, so limit the agent to the operations it needs, such as listing voices or generating audio, and leave the rest out of the allowed set. You choose which of the five operations it may call.
- **Credential handling:** Your Fliki token is stored once, encrypted, by your own Jentic One instance and injected into the Authorization header at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'generate a video from text' or 'list available voices', and Jentic returns the matching Fliki operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **ElevenLabs API** — ElevenLabs is a voice-only TTS provider with extensive voice cloning options
- **Synthesia API** — Synthesia generates avatar-led videos rather than voiceover-over-stock-footage
- **HeyGen API** — HeyGen provides avatar video generation that can pair with Fliki for varied output formats

## FAQ

### What authentication does the Fliki API use?

The Fliki API uses HTTP bearer tokens issued from a Fliki Enterprise account. Through Jentic the bearer token is held in the encrypted vault and injected into the Authorization header at execution time.

### Can I generate a video from a script with the Fliki API?

Yes. POST your script to `/generate/video` with a chosen voice and Fliki returns a finished MP4 with synchronized voiceover.

### How do I choose which voice to use?

Call GET /voices to list available voices with their language, dialect, gender, and style attributes, then pass the chosen voice ID to `/generate/audio` or `/generate/video.`

### What are the rate limits for the Fliki API?

The Fliki API does not document a fixed rate limit in the spec. Generation throughput depends on your Enterprise plan. Treat 429 responses as the source of truth and back off using the Retry-After header.

### How do I generate an AI voiceover through Jentic?

Search Jentic for 'generate an AI voiceover', load the schema for `/generate/audio`, and execute the call with your script and a chosen voice. Install with pip install jentic and run it through Jentic One, the self-hosted execution layer.

### Is the Fliki API free?

API access is part of Fliki's Enterprise tier rather than the standard product. Confirm the current pricing on fliki.ai before integrating.

### Can I limit what my agent is allowed to do with the Fliki API?

Yes. Because you run Jentic One yourself, your own rules decide which of Fliki's five operations the agent may call, so you can allow it to list voices, languages, and dialects while blocking the generation endpoints, or permit only `/generate/audio` and leave `/generate/video` out. Since Fliki carries its generation target in the request body rather than as a resource in the URL path, scoping is done at the operation level: you grant just the calls the agent needs and withhold the rest. The Fliki bearer token stays with your Jentic One instance and is added to the request only for operations you have allowed.