Aivoov

@Aivoov show me all available English voices with their characteristics and supported styles

Found 12 English voices across US, UK, and Australian accents. Sample entries: 'Emma' (US, female, warm tone, supports conversational and professional styles), 'James' (UK, male, authoritative, supports narrative and instructional styles), 'Olivia' (AU, female, friendly, supports casual and upbeat styles). Each voice includes age range, pitch characteristics, and recommended use cases. Full list includes voice IDs needed for synthesis requests.

This example demonstrates the MCP's core discovery function — mapping the voice inventory before generating audio. The API key must be valid to retrieve this catalog. Voice availability can change as Aivoov updates their library, so treat this as a point-in-time snapshot rather than a permanent reference.

@Aivoov filter voices by Spanish language and identify which ones support both formal and casual speaking styles

Filtered to 8 Spanish voices. Three support both formal and casual styles: 'Carlos' (ES-Spain, male, versatile range, works for corporate training and podcast intros), 'Sofia' (MX-Mexico, female, adaptable tone, suitable for customer service and storytelling), 'Diego' (AR-Argentina, male, dynamic delivery, handles business presentations and conversational content). The remaining five voices specialize in single-style delivery.

Shows how the MCP helps narrow voice selection by language and style requirements before committing to audio generation. This filtering happens client-side after retrieving the full catalog — the MCP fetches all voices, then the AI applies your criteria. Useful when planning multilingual content workflows or matching voice personality to brand guidelines.

@Aivoov compare the voice options for a medical training narration — I need clarity and a reassuring tone, preferably female

Recommended three voices from the catalog: 'Dr. Sarah' (US, designed for healthcare content, clear enunciation, calm pacing), 'Rachel' (UK, professional tone with warmth, high intelligibility scores), 'Nina' (CA-Canada, steady delivery, tested for technical terminology). All three support slower playback speeds and emphasize consonant clarity. 'Dr. Sarah' has the most extensive medical vocabulary training. Each voice ID is ready for synthesis API calls.

Illustrates how the AI can reason over voice metadata to match use-case requirements. The MCP provides the raw voice catalog; the AI interprets characteristics like 'clarity' and 'reassuring' against your brief. This workflow assumes Aivoov tags voices with descriptive metadata — if tags are sparse, recommendations rely on voice names and basic attributes only.

When Aivoov fits a small content team's localization workflow

A 3-person video team ships tutorial content in English, Spanish, and French. They need to scout voice options before recording sessions, not during. Aivoov's single tool lets them pull the full voice catalog filtered by language, then share candidates in Switchy threads before booking studio time. The API key setup is straightforward—no OAuth dance. The limitation: you're only browsing voices here, not generating audio or managing projects. If your team needs end-to-end TTS orchestration (script upload, rendering, asset management), this MCP is too narrow. But if you're in the planning phase and need a quick voice reference library across languages, Aivoov keeps that step out of your vendor's web portal and inside your workspace.

Why this MCP works for early-stage audio branding decisions

A two-founder startup is launching a podcast and needs to pick a voice for the intro bumper. They're comparing 8-10 options across tone and accent before committing to a voice actor or TTS service. Aivoov's list tool gives them a filterable catalog they can review in a shared Switchy chat, tagging favorites and ruling out mismatches in real time. The single-tool scope is a feature here: there's no workflow bloat, just a reference lookup. The catch: if you're already deep into a TTS platform with its own voice library, adding this MCP is redundant. Use Aivoov when you're platform-shopping or need a neutral voice index that isn't locked to one vendor's ecosystem.

When Aivoov supports compliance planning but not execution

A 6-person product team is scoping an accessibility overhaul that includes screen-reader-friendly audio descriptions. They need to survey which voices support their user base's top 5 languages and document the options for a compliance report. Aivoov's language-filtered voice list gives them a snapshot they can export into a planning doc without logging into a TTS vendor's dashboard. The API key auth means one team member can provision access for the whole group in under a minute. The boundary: this MCP doesn't generate audio, test pronunciation, or integrate with your CMS. If your audit requires sample clips or live testing, you'll need a fuller TTS integration. Aivoov is the research step, not the build step.