ActVoice
Audio drama studio for humans and AI agents.
ActVoice turns a text project manifest into a rendered audio drama: characters, voices, scenes, dialogue, ambience, sound cues, and a final MP3 artifact.
Screen-reader friendly workflow
No visual timeline required. The core workflow is text-first: create a project, add characters, add scenes, add dialogue lines, add semantic sound cues, then render.
Everything important is available through REST API and MCP tools, so a blind creator can work through a screen reader, terminal, or AI agent.
Quick start for agents
- 1. Register an agent. Call
POST /api/agents/registerand receive an ActVoice API key. - 2. Connect with MCP. Local clients can run
python -m app.mcp_server. Future remote clients will connect tohttps://actvoice.xyz/mcp. - 3. Create a project. Use MCP tool
create_audio_drama_projector REST endpointPOST /api/projects. - 4. Build the script. Add characters, scenes, dialogue lines, and semantic sound cues like
footsteps,brook,birds, orlaptop_close. - 5. Place sounds with timing anchors. Agents can use absolute
start_msor relative anchors such asafter_lineplusline_idandoffset_ms. ActVoice measures rendered lines and writes a timing map; no AI runs inside the core service. - 6. Render. Call
render_final_mixorPOST /api/projects/{project_id}/render. REST rendering is queued and returns a job id; pollGET /api/jobs/{job_id}. - 7. Download artifacts. When the job is done, fetch metadata or files from
/api/projects/{project_id}/artifact,/artifact.mp3,/artifact.wav, or/render-manifest.json.
Authentication
Write and render actions require a bearer key:
Authorization: Bearer [REDACTED]
For local stdio MCP, the same key can be provided as ACTVOICE_API_KEY. For remote HTTP MCP, the same idea becomes header-based transport authentication.
Voice and rendering modes
rhvoice: current free local/server-side mode.openai_byo_key: planned user-provided paid provider mode.edge: planned experimental fallback mode.
Service endpoints
- Health:
/health - Voices:
/api/voices - OpenAPI schema:
/docs