Or jump from this list on a smaller screen.
This is a page from the Audivra documentation. Developer exports — index: http://127.0.0.1:3000/docs/llms.txt, full corpus: http://127.0.0.1:3000/docs/llms-full.txt, OpenAPI: http://127.0.0.1:3000/docs/openapi.json, Postman: http://127.0.0.1:3000/docs/postman.json. Press ⌘K to search docs.
Models
TTS, video, and local engines control quality, latency, VRAM footprint, language coverage, and plan tier gates.
Per-request text is capped at 5,000 characters across cloud API routes. Local fast-path engines use shorter limits — see Local worker.
Speech models
| model | Name | Latency | Languages | Max text | License | VRAM | Tier |
|---|---|---|---|---|---|---|---|
| kokoro-82m | Kokoro-82M | Ultra-fast | en-US, sw-KE, ha-NG, yo-NG, am-ET, hi-IN, bn-IN, de-DE, it-IT, nl-NL, zu-ZA | 5,000 | Apache 2.0 | Low (T4) | All plans |
| kokoro | Kokoro | Fast | en-US, en-GB | 5,000 | Apache 2.0 | Low | All plans |
| f5-tts | F5-TTS | Streaming | en-US, Clone any language (Starter+) | 5,000 | MIT | Med | All plans |
| xtts-v2 | XTTS v2 | Clone | ja-JP, 17+ clone languages | 5,000 | Coqui | Med | Starter+ |
| cosyvoice-2 | CosyVoice 2 | Expressive | fr-FR | 5,000 | Apache 2.0 | High | Creator Pro+ |
Video / lip-sync models
musetalk
MuseTalk · Video lip-sync
Moderate · Apache 2.0 · VRAM: Med
Languages: Language-agnostic (audio-driven)
Max text: 5,000 chars · Tier: All plans
latentsync
LatentSync · Fast lip-sync
Fast · Apache 2.0 · VRAM: Low
Languages: Language-agnostic (audio-driven)
Max text: 5,000 chars · Tier: All plans
liveportrait
LivePortrait · Photo expressions
Moderate · Research · VRAM: Med
Languages: Language-agnostic (audio-driven)
Max text: 5,000 chars · Tier: Starter+
sadtalker
SadTalker · Audio-driven portrait
Moderate · MIT · VRAM: Med
Languages: Language-agnostic (audio-driven)
Max text: 5,000 chars · Tier: All plans
emo
EMO · Expressive generation
Slow · Research · VRAM: High
Languages: Language-agnostic (audio-driven)
Max text: 5,000 chars · Tier: Creator Pro+
codeformer
CodeFormer · Face enhancement
Fast · Non-commercial · VRAM: Low
Languages: N/A (post-processing)
Max text: 5,000 chars · Tier: Starter+
Local / self-hosted
ollama-qwen
Ollama — Qwen2.5 3B · Fast local LLM
Local (<500 chars) · Apache 2.0 · ~2.5 GB
Languages: Multilingual
Max text: 500 chars · Tier: Self-hosted
ollama-llama
Ollama — Llama 3.2 3B · Fast local LLM
Local (<500 chars) · Llama 3.2 · ~2.5 GB
Languages: Multilingual
Max text: 500 chars · Tier: Self-hosted
piper-tts
Piper TTS · CPU-friendly TTS
Ultra-fast · MIT · CPU
Languages: en-US, Regional packs
Max text: 500 chars · Tier: Self-hosted
Self-hosted stack details: Local worker