Offline workflow
Useful for teams that need unlimited speech generation without recurring cloud API costs.
Features
What is included.
FrostSpeech TTS is built for Unity teams creating RPG dialogue, prototype voiceovers, final character voices, and large volumes of speech assets without leaving the Editor.
The tool integrates local neural TTS engines such as Piper and Sherpa-ONNX, including Kokoro-compatible model workflows, so teams can generate unlimited speech offline without monthly cloud API costs.
For projects that need premium hosted voices, FrostSpeech can switch to ElevenLabs and generate cloud audio directly in the Unity project using your own API key.
Generated audio is automatically written, imported into the Unity Asset Database, and prepared as AudioClip assets, with character-specific FrostSpeechTTSProfile ScriptableObjects for consistent voice settings.
A setup wizard downloads the required platform binaries and voice models on demand, keeping the package clean while still making first-run setup fast.
100% offline generation with local Piper and Sherpa-ONNX engines
Support for realistic open-source voice models, including Kokoro model workflows
Optional ElevenLabs cloud integration using your own API key
Automatic .wav and .mp3 import into the Unity Asset Database
Generation controls for speed, pitch, noise scale, and voice settings
FrostSpeechTTSProfile ScriptableObjects for per-character voice consistency
One-click setup wizard for platform binaries and model downloads
FrostSpeechAPI for async scripted generation from custom tools or dialogue systems
Reviews
Product review notes.
Customer feedback, setup notes, and production impressions from Unity users.
Editor integration
Generated audio lands directly in the Unity Asset Database as ready-to-use clips.
Character consistency
Profile assets keep engine, voice model, speed, and pitch settings consistent across a cast.
Similar products
More Unity tools.
Other Frostember assets for production workflows, editor tooling, and Unity project pipelines.
LiveAudio Lip Sync & Facial Animation
FaceSync
FaceSync generates lip-sync and facial animation inside Unity from audio, with baked playback, Timeline workflows, runtime playback, live microphone input, procedural...
View product
LiveKanban Task Management
FrostBoard
FrostBoard is a native Unity Editor Kanban board for task planning, team workflow, project asset links, task details, templates, search, swimlanes, and undoable board...
View product
In productionBranching Conversations for Unity
Dialogue System
A node-based dialogue workflow for quests, branching lines, speaker data, conditions, and Unity runtime playback.
Coming soon