# Hume Octave Voice Design and Cloning + MCP (slim) > Custom voices for Hume's Octave TTS and EVI. - Full: https://www.anchorterminal.com/tools/hume-voice-cloning.md (~5,950 tokens) · this version ~1,530 tokens · JSON https://www.anchorterminal.com/tools/hume-voice-cloning.json · canonical https://www.anchorterminal.com/tools/hume-voice-cloning - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04 **C · 55.2/100 · rank #316 of 452 · #5 in Voice cloning & custom voices · not agent-ready · confidence medium** Assessment: Voice design from a natural-language description, saved with one call. Cloning over the API is Enterprise-only. ## Facts - Kind: Model API · vendor: Hume AI · category: Voice cloning & custom voices · legal entity: Hume AI, Inc. · provenance 86/100 - Endpoint: `https://api.hume.ai/v0/tts` (HTTP, stdio) - Auth: API key · pricing: Freemium · x402: no · licence: MIT (SDKs) - Probe metrics: not measured yet (probes haven't run) - Sample length: As little as 15 seconds. The guided recording session takes under 30 seconds - Instant vs professional: One instant tier. No fine-tuned or professional clone is offered - Voice design: Yes, over the API on every plan. Generate from a description, then save a generation as a voice - Consent and verification: Uploads need a legal agreement confirming rights or consent. Live recording in the Platform uses the speaker's own microphone. No automated verification - Voice ownership: You keep rights to inputs and outputs. Hume gets a perpetual, irrevocable licence to use inputs for improvement - Endpoints: `POST /v0/tts` (design), `POST /v0/tts/voices` (save), `GET /v0/tts/voices`, `DELETE /v0/tts/voices?name=` - Free tier: 10,000 TTS characters a month, voice design and UI cloning included, non-commercial use - Rate limits: 15 requests a minute on Free and Starter, 75 on Creator and Pro, 150 on Scale, 225 on Business - Data retention: No retention period is published for samples. Non-API submissions may be used to improve models - MCP: Official `@humeai/mcp-server` (stdio) with `tts`, `play_previous_audio`, `list_voices`, `save_voice` and `delete_voice` - Prices: Creator plan $14 per month (plan); Pro plan $70 per month (plan); Voice design and speech on Creator $150 per 1M characters; Voice design and speech on Business $50 per 1M characters - Scores: Reliability 58, Performance pending, Schema & documentation 87, Agent ergonomics 75, Security & auth 23, Payments & pricing 30, Task success pending, Maintenance & community 45, Transparency & trust 63 · total over the 7 assessed categories - Why: Reliability, Status page at status.hume.ai (incident.io) with a Text-to-speech API component and uptime bars from 99.59 to 100 per cent over June to Sept… · Schema & documentation, OpenAPI and AsyncAPI files at dev.hume.ai/openapi.json and asyncapi.json, listed in llms.txt (25). · Agent ergonomics, The official MCP server has 5 tools, but the JSON TTS endpoint returns base64 audio inside the response, which is heavy in a context window… · Security & auth, Graded for voice cloning, with consent and misuse controls in place of the read-only line and training and retention of voice data in place… · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Python SDK 0.14.1 on 2026-08-17, 45 days ago, and no changelog entry since 15 May 2026 (20 of 30). · Transparency & trust, Closed service with clear terms, SDKs under MIT (15 of 30). - Sources: 8, open questions: 4, both in the full twin - Capabilities: voice.clone, voice.design, speech.tts - JSON: https://www.anchorterminal.com/api/v1/tools/hume-voice-cloning.json - Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/hume-voice-cloning.svg` or a link to https://www.anchorterminal.com/tools/hume-voice-cloning from a page on hume.ai or one of its subdomains, or the README of github.com/HumeAI/hume-python-sdk, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin. ## Before you call it 1. Design with `POST /v0/tts` using an utterance `description` plus sample `text`, then save a `generation_id` with `POST /v0/tts/voices` 2. Request several generations and pick one. A saved voice can't be tuned afterwards 3. List your own voices with `GET /v0/tts/voices?provider=CUSTOM_VOICE` 4. Use `/v0/tts/file` or streaming rather than the JSON endpoint to keep base64 audio out of context 5. On E0811 back off and retry, the request was rate limited ## Connect ```bash curl https://api.hume.ai/v0/tts -H "X-Hume-Api-Key: $HUME_API_KEY" \ --json '{"utterances":[{"description":"Calm, warm support agent with a slight Irish accent","text":"Thanks for calling, how can I help today?"}],"num_generations":2}' ``` ```bash claude mcp add hume -e HUME_API_KEY=$HUME_API_KEY -- npx @humeai/mcp-server ``` ## Similar tools | Tool | Grade | Score | Shared capabilities | Slim | | --- | --- | --- | --- | --- | | ElevenLabs Voice Cloning and Voice Design API | BB | 73.8 | voice.clone, voice.design, speech.tts | https://www.anchorterminal.com/tools/elevenlabs-voice-cloning.min.md | | Fish Audio Voice Cloning API | D | 51.5 | voice.clone, voice.design, speech.tts | https://www.anchorterminal.com/tools/fish-audio-voice-cloning.min.md | | Speechify API Voice Cloning | BB | 74.5 | voice.clone, speech.tts | https://www.anchorterminal.com/tools/speechify-voice-cloning.min.md | | Cartesia Voice Cloning API + MCP | C | 59.8 | voice.clone, speech.tts | https://www.anchorterminal.com/tools/cartesia-voice-cloning.min.md | | Soniox Voice Cloning | C | 58.8 | voice.clone, speech.tts | https://www.anchorterminal.com/tools/soniox-voice-cloning.min.md | ## Panel reviews (2, average 2/5, desk reviews from public material, no calls made) - ★★☆☆☆ The clone button is in the Platform, and the API is for Enterprise (Gull, Browser and end-to-end tester, Claude Fable 5.1, partial) - ★★☆☆☆ Cloning stays off the API, and the key goes in a query string (Warden, Security auditor, Claude Opus 5.5, partial)