Skip to main content
Fish Audio logo
  • Category: audio & speech
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 12
  • Triggers: 0
  • Slug: FISH_AUDIO
  • Version: 20261101_00
  • Instant: Supported on the latest version. Support varies by tool.

Tools

Slug: FISH_AUDIO_CONFIGURE_AGENTPartially update an agent’s draft prompt, voice, and core conversation behavior without publishing it.

Input Parameters

string
required
Agent ID to configure.
string
Conversation timezone, up to 64 characters.
string ("relaxed" | "balanced" | "eager")
Response timing: relaxed, balanced, or eager.
boolean
Whether future sessions should record audio.
string
Fixed greeting text when first_message_mode is fixed.
boolean
Whether callers may interrupt the agent while it speaks.
string
Replacement draft system prompt; Fish Audio limits it to 4000 tokens.
string
Replacement voice model ID returned by List Voice Models.
string ("en" | "ja" | "zh" | "ko" | "es" | "fr" | "de")
Speaking language: en, ja, zh, ko, es, fr, or de.
string ("off" | "fixed" | "prompt")
Greeting mode: off, fixed, or prompt.
string
Instructions for generating the greeting when first_message_mode is prompt.
integer
Maximum session duration from 60 to 3600 seconds.
string ("low" | "balanced" | "high")
Interruption sensitivity: low, balanced, or high.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_CREATE_AGENTCreate a private Fish Audio agent, optionally with an initial prompt, voice, and core conversation settings. The new agent remains a draft until separately published.

Input Parameters

string
required
Agent name (1-120 characters).
string
Agent purpose or operator-facing description (up to 2000 characters).
boolean
Whether sessions should record audio.
string
Fixed initial greeting when first_message_mode is fixed.
string
Initial system prompt; Fish Audio limits it to 4000 tokens.
string
Voice model ID returned by List Voice Models.
string ("en" | "ja" | "zh" | "ko" | "es" | "fr" | "de")
Speaking language: en, ja, zh, ko, es, fr, or de.
string ("off" | "fixed" | "prompt")
Initial greeting mode: off, fixed, or prompt.
integer
Maximum session duration from 60 to 3600 seconds.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_DELETE_AGENTPermanently delete a Fish Audio agent by ID; use only when deletion is explicitly intended.

Input Parameters

string
required
ID of the agent to permanently delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_DESIGN_VOICEGenerate original voice previews synchronously from a voice description, without cloning or saving a voice model.Instant: Supported on the latest version.Instant pricing: $0.01 per successful voice-design request (1–4 candidates)

Input Parameters

integer
Number of voice candidates (1–4); the request is billed once.
integer
Optional deterministic generation seed.
number
Preview speaking speed multiplier, greater than zero and at most 3.
string
Optional BCP-47 language hint, such as en or ja.
integer
Number of diffusion steps (1–128).
string
required
Describe the desired original voice; do not impersonate an identifiable person.
number
Nonnegative classifier-free guidance scale.
string
Optional preview text, up to 150 characters.
number
Nonnegative instruction guidance scale.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_GET_ACCOUNT_BALANCEReturn the connected Fish Audio account’s package allowance and API credit to distinguish package quota from paid credit. An optional team ID selects the team for the API-credit lookup; the package lookup remains for the connected account.

Input Parameters

string
Optional team ID whose API credit should be checked; omit for the connected account’s active workspace.
boolean
Ask Fish Audio to include current free-credit eligibility in the API-credit result.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_GET_AGENTReturn an agent’s workspace metadata together with its current draft conversation configuration.

Input Parameters

string
required
Agent ID returned by List Agents or Create Agent.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_GET_VOICE_MODELGet a Fish Audio voice model by ID and inspect whether it is trained and suitable for synthesis.

Input Parameters

string
required
Voice model ID returned by List Voice Models.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_LIST_AGENTSSearch agents in the connected Fish Audio workspace, including draft or archived agents when requested.

Input Parameters

Case-insensitive search across agent names and descriptions.
integer
Maximum agents to return in this page (1-100).
string
Continuation cursor from a previous response. Omit for the first page; pass it back unchanged to fetch the next page.
boolean
Whether to include archived agents.
string ("all" | "live" | "draft")
Publication state to include: all, live, or draft.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_LIST_AGENT_SESSIONSList conversation sessions for the workspace or a specific agent, filtered by lifecycle status, caller, or creation time.

Input Parameters

string
Only return sessions belonging to this agent ID.
array
Lifecycle statuses to include: pending, active, completed, failed, or unknown. A comma-separated string is also accepted.
integer
Maximum sessions to return in this page (1-100).
string
Continuation cursor from a previous response. Omit for the first page; pass it back unchanged to fetch the next page.
string
Exact E.164 caller number for phone sessions.
string
Return sessions created after this ISO 8601 timestamp.
string
Return sessions created before this ISO 8601 timestamp.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_LIST_VOICE_MODELSSearch public or workspace-owned Fish Audio voice models. Before synthesis, select an item whose type is tts; svc model IDs are not compatible with TTS.

Input Parameters

array
Filter by one or more model tags. A single or comma-separated string is accepted.
string
Filter models by title.
string ("score" | "task_count" | "created_at")
Sort models by score, task_count, or created_at.
boolean
When true, discover only voices whose rights Fish Audio has secured; ignored by the provider for owned_only listings.
string
Filter public models by author ID; ignored when owned_only is true.
array
Filter by one or more language codes such as en, es, or ja.
integer
Maximum models in this page (1-100).
boolean
Return only models owned by the active workspace instead of public discovery models.
string
Continuation cursor returned by a previous call; omit for the first page.
array
Optional title-language filters.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_SYNTHESIZE_SPEECHGenerate downloadable speech synchronously using a Fish Audio model and voice IDs. With your own key the default is free S2.1; managed requests default to paid S2.1 Pro, require paid models and public, licensed, trained TTS voices, and are limited to 10,000 UTF-8 bytes and four voices.Instant: Supported on the latest version.Instant pricing: $0.015 per 1,000 bytes of text; non-English characters use more bytes

Input Parameters

string
required
Text to synthesize. For multiple voices, use <|speaker:0|>, <|speaker:1|>, and matching indexes in voice_model_ids.
string ("s2.1-pro-free" | "s2.1-pro" | "s2-pro" | "s1")
Speech model. If omitted, defaults to free s2.1-pro-free when you connect your own Fish Audio key, otherwise to paid s2.1-pro. Without your own key, only paid models (s2.1-pro, s2-pro, s1) and public licensed voices are available. Preview models are excluded.
number
Speaking-rate multiplier from 0.5 to 2.0.
number
Nucleus-sampling diversity from 0 to 1.
string ("mp3" | "wav" | "pcm" | "opus")
Output format: mp3, wav, pcm, or opus.
number
Output volume adjustment in decibels.
string ("normal" | "balanced" | "low")
Latency-quality tradeoff: normal, balanced, or low.
number
Expressiveness from 0 to 1; higher values are more varied.
boolean
Normalize English and Chinese text, including numbers, before synthesis.
array
required
One voice model ID for normal speech, or multiple IDs in speaker-tag order for dialogue. A single string is accepted as a one-item list.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: FISH_AUDIO_TRANSCRIBE_AUDIOTranscribe a previously uploaded audio file synchronously with Fish Audio. First upload through Composio files.upload in the SDK or the file-upload API; pass the returned file object, not a raw URL. Audio must be at most 64 MiB (a stricter platform limit may apply). Returns text, duration, optional segment timestamps and detected language. Long recordings may take several minutes.Instant: Supported on the latest version.Instant pricing: $0.36 per audio hour, rounded up to the next second per successful request

Input Parameters

object
required
Upload the recording first using Composio files.upload in the SDK or POST /api/v3.1/files/upload/request followed by uploading the bytes. Pass the returned file object here. Maximum 64 MiB; a raw URL or local filename alone is not accepted. Use audio you own or have permission to transcribe.
string ("transcribe-1" | "transcribe-1-pro")
Speech-to-text model; both models have the same published rate.
string
Optional language hint; Fish Audio still auto-detects the language.
boolean
Whether to omit precise timestamps; false can increase latency for short recordings.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not