ElevenLabs API for your agent: voices, transcripts, sound effects and music

    Let your AI agent speak, transcribe and score with ElevenLabs: text to speech with eleven_v4, multi-voice dialogue, Scribe speech to text, sound effects, music, voice changing and noise removal. You need no ElevenLabs account or API key. Your agent runs each job from your Agensi balance and tells you what it cost.

    9 tools on Agensi
    Voice 8
    Music 1
    elevenlabs.io

    Use any of these from your AI Agent, with no ElevenLabs account or API key. Your AI Agent works out the exact price, runs the tool from your balance and tells you what it cost. Failed uses are free.

    Connect your AI Agent

    All ElevenLabs tools and prices

    • ElevenLabs Voice Isolator

      $0.156 per minute

      Voice
      The tool you opened
      New

      Voice isolation / noise removal: pass an HTTPS audio_url (max 20MB — Agensi fetches and relays it), get back the isolated speech as base64 audio. Provide expected_duration_minutes to size the admission hold. KNOWN RISK: outputs beyond ~2 minutes can exceed the run-payload bound — prefer short clips.

    • ElevenLabs Forced Alignment

      $0.0048 per minute

      Voice
      New

      Forced alignment: pass an HTTPS audio_url (max 20MB — Agensi fetches and relays it) plus the transcript text (plain string), get word-level {text, start, end} timings with per-word confidence. Need the transcript too? Use /v1/speech-to-text instead.

    • ElevenLabs List Voices

      Free

      Voice
      New

      List the ElevenLabs voices available to this account (voice_id, name, category, labels, preview_url).

    • ElevenLabs Sound Effects

      $0.156 per minute

      Voice
      New

      Text-to-sound-effects: describe the sound ('Heavy wooden door creaking open', 'Atmospheric synth pad') and set duration_seconds (0.5–30, required — it is the billing basis). Output is MP3 base64 (audio_base64).

    • ElevenLabs Speech to Text

      $0.0048 per minute

      Voice
      New

      Speech-to-text transcription (ElevenLabs Scribe). Pass an HTTPS audio_url (public or presigned; video and YouTube/TikTok URLs work too) — ElevenLabs fetches the media itself. Returns the transcript text with per-word timestamps, speakers and detected entities. Provide expected_duration_minutes to size the admission hold; billing settles on the actual audio duration.

    • ElevenLabs Text to Dialogue

      $0.052 per 1,000 characters

      Voice
      New

      Multi-speaker text-to-dialogue: pass ordered {text, voice_id} pairs (voices from /voices, up to 10 unique) and get one continuous MP3 with distinct speakers, emotional audio tags ([giggling], [whispering]) supported. The generated MP3 is saved in Agensi's storage; the run output carries an `audio` object with a fresh signed download_link (plus content_type and the billed character_count). Supports eleven_v4 (default), eleven_v4_turbo at half price and eleven_v3, plus seed and previous_text/future_text continuity for scripts split across runs. Priced per character.

    • ElevenLabs Text to Speech

      $0.052 per 1,000 characters

      Voice
      New

      Generate speech from text with ElevenLabs. Choose a voice via voice_id (from /voices) and a model (eleven_v4 by default for the most expressive delivery with audio tags like [whispering], eleven_v4_turbo for the same family at half price, eleven_multilingual_v2 for speed and style controls, eleven_flash_v2_5 for half price and the fastest render, eleven_v3 for the previous expressive model). The generated MP3 is saved in Agensi's storage; the run output carries an `audio` object with a fresh signed download_link (plus content_type and the billed character_count). Priced per character.

    • ElevenLabs Voice Changer

      $0.156 per minute

      Voice
      New

      Voice changer (speech-to-speech): pass an HTTPS audio_url (max 20MB / 5 minutes — Agensi fetches and relays it) and a target voice_id from /voices; whispers, laughs and accents survive the conversion. Output is base64 MP3. KNOWN RISK: outputs beyond ~2 minutes can exceed the run-payload bound.

    • ElevenLabs Music Generation

      $0.195 per minute

      Music
      New

      Text-to-music: describe genre, mood, instrumentation and vocals, set music_length_ms (3s–120s, required — it is the billing basis). Output is MP3 base64 (audio_base64). Generation takes up to a few minutes — this endpoint has an extended timeout.

    Starting prices. Prices can vary with length and quality. Your AI Agent works out the exact price, runs the tool from your balance and tells you what it cost. Failed uses are free.

    What do you want your agent to do?

    • Read a script aloud

      Text to Speech with eleven_v4 gives the most expressive delivery and follows tags such as [whispering]. Turbo and Flash cost less.

    • Make a conversation

      Text to Dialogue turns a script with up to 10 voices into one continuous MP3 with distinct speakers.

    • Transcribe audio or video

      Scribe returns the transcript with word timestamps and speakers, from a file or a YouTube or TikTok link.

    • Add a sound effect

      Describe a sound, such as a heavy wooden door creaking open, and get up to 30 seconds of audio.

    • Make background music

      Describe the genre, mood and instruments and get a track of up to two minutes.

    • Clean up a noisy recording

      Voice Isolator removes background noise and keeps the speech. It works best on short clips.

    How to choose the best ElevenLabs tool or MCP for you

    Pick the voice model

    eleven_v4 for the most expressive reads, eleven_v4_turbo for the same family at a lower price, eleven_flash_v2_5 for the fastest render, eleven_multilingual_v2 for speed and style controls.

    Choose a voice first

    Listing voices is free. Your agent can show you names, labels and preview links, then use the voice you pick.

    Priced by length

    Speech and dialogue are priced per character. Transcription, sound effects, music and the voice tools are priced per second of audio.

    Keep some clips short

    Voice Changer and Voice Isolator suit short clips, so split a long recording into parts first.

    If you needChooseToday's price
    A voice-over for a video or adElevenLabs Text to Speech
    A podcast-style talk between hostsElevenLabs Text to Dialogue
    Subtitles or notes from a recordingElevenLabs Speech to Text (Scribe)
    Word timings for a transcript you already haveElevenLabs Forced Alignment
    A whoosh, click or crowd soundElevenLabs Sound Effects
    Your recording in a different voiceElevenLabs Voice Changer
    A short music bedElevenLabs Music Generation

    Quick picks: Text to Speech for voice-overs, Text to Dialogue for podcasts, Scribe for transcripts, Music Generation for music beds.

    Why use Agensi instead of separate ElevenLabs MCPs?

    ElevenLabs runs its own hosted MCP server: you sign in with your ElevenLabs account and use your plan, and it can also manage ElevenLabs voice agents. Through Agensi you need no ElevenLabs account. Your agent pays per use from the same balance as Kling, Veo and our data tools, keeps the audio files for you, and tells you what each job cost.

    What you getOfficial MCP per brandOwn API key or community serverAgensi
    AccountsOne per brandOne per brandOne
    API keysPer brand, or a sign-inPer brand, kept by youNone
    PaymentA plan or credits per brandPer brandOne balance, per use
    Spending controlVariesUp to youLimits per use, day and month, or ask first
    Several sources in one answerConnect several serversSeveral servers and keysOne connection
    Skills for the whole jobNoNoYes, from the marketplace

    When another way is the better choice. ElevenLabs' own MCP server or API is the better choice if you already pay for a plan, want voices you cloned or designed in your ElevenLabs account, or build ElevenLabs voice agents. Through Agensi you choose from the voices we offer, and voice cloning isn't available.

    Set up in your AI agent

    Connect your AI agent to Agensi once, sign in and click Allow. After that it can use every tool: it runs one from your balance and tells you what it cost. No API keys or provider accounts.

    1. Open Settings, then Connectors, then Browse connectors and add Agensi (or Add custom connector and paste https://mcp.agensi.io/mcp/auth).
    2. Sign in to Agensi and click Allow. One agent per account: connecting a new one disconnects the old one.
    3. Ask for what you want, for example: "Use Agensi to turn this script into a calm voice-over and add a minute of soft background music under it." Top up from $5 if your balance is low; failed uses are free.

    Grok, VS Code, GitHub Copilot, Cline, Kiro and other agents with remote MCP and sign-in work too: see the setup guide.

    What it costs: a worked example

    "Use Agensi to turn this script into a calm voice-over and add a minute of soft background music under it."

    • 1 × List voices to pick one

    • 1 × Voice-over, about 1,000 characters

    • 1 × One minute of background music

    Your agent works out the exact price for your request and tells you what it cost.

    Combine ElevenLabs tools with skills

    ElevenLabs MCP: frequently asked questions

    Yes. ElevenLabs runs a hosted MCP server that you connect with your ElevenLabs account, and its older local server is deprecated. Agensi is a separate route: no ElevenLabs account or key, ElevenLabs next to other voice, video and data tools, and one balance for all of them.

    Each ElevenLabs tool on this page shows its live price. Speech and dialogue are priced per character, and the other audio tools per second. Your agent works out the exact price, runs the job from your balance and tells you what it cost. Listing voices is free, and failed uses are free too.

    Not through Agensi. You choose from the ElevenLabs voices we offer, and your agent can list them with preview links for free. If you need your own cloned or designed voice, use ElevenLabs directly with your own account, through its website, API or MCP server.

    No. Connect your AI agent to Agensi and add funds to your balance. Your agent runs ElevenLabs from that balance while it covers the price, or asks first if you choose that in your Dashboard under Balance. Audio links work for 7 days, and the files stay in your Dashboard for 30 days.

    Read next

    Browse all tools